INDEX

Explanations

mentions of famous individuals or works in various fields, potentially related to influential figures or significant achievements

oai_token-act-pair · gpt-3.5-turbo

possessive forms and references to specific notable individuals

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 discrep

-0.74

 antioxid

-0.74

tnc

-0.73

 overload

-0.66

Els

-0.66

 deterrent

-0.63

reen

-0.62

 cohesion

-0.62

 hostilities

-0.62

DATA

-0.61

POSITIVE LOGITS

Jr

1.10

enegger

0.97

Sr

0.87

 famously

0.85

 assassinated

0.84

ÃĥÃĤ

0.84

otype

0.78

 Dracula

0.75

 Himself

0.73

akespe

0.73

Activations Density 0.669%

mentions of famous individuals or works in various fields, potentially related to influential figures or significant achievements

possessive forms and references to specific notable individuals

No Comments

No Known Activations