INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of 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

ously

-0.79

emonic

-0.72

posed

-0.71

oat

-0.71

antically

-0.71

stick

-0.70

fix

-0.70

oxide

-0.69

Pont

-0.68

optim

-0.68

POSITIVE LOGITS

 Introduced

0.74

externalActionCode

0.72

 Companies

0.70

TPPStreamerBot

0.67

 complied

0.66

LLP

0.65

{*

0.64

icum

0.63

 CLSID

0.63

 Extras

0.63

Activations Density 0.032%

proper nouns related to individuals

proper nouns, specifically names of individuals

No Comments

No Known Activations