INDEX

Explanations

specific details or conditions that are emphasized or singled out

oai_token-act-pair · gpt-3.5-turbo

references to "certain" criteria or conditions

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

DragonMagazine

-0.81

inson

-0.73

TeX

-0.72

perse

-0.71

ITAL

-0.70

Cum

-0.69

 thence

-0.69

annis

-0.68

INT

-0.68

JV

-0.68

POSITIVE LOGITS

ties

1.45

 kinds

1.19

 types

1.00

 wavelengths

0.93

iated

0.90

 aspects

0.89

iating

0.89

 circumstances

0.83

 parts

0.82

 regions

0.82

Activations Density 0.022%

specific details or conditions that are emphasized or singled out

references to "certain" criteria or conditions

No Comments

No Known Activations