INDEX

Explanations

phrases related to legal and regulatory issues

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in."

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

USB

-0.76

CLASSIFIED

-0.70

âĿ

-0.66

 surpr

-0.66

oola

-0.65

 convol

-0.65

å°Ĩ

-0.64

ç·

-0.64

STAR

-0.64

ALSE

-0.64

POSITIVE LOGITS

 lieu

1.38

 accordance

1.29

effic

1.22

efficiency

1.19

clusions

1.17

 vitro

1.14

 conjunction

1.12

 favor

1.10

versions

1.06

 disguise

1.05

Activations Density 0.458%

phrases related to legal and regulatory issues

occurrences of the word "in."

No Comments

No Known Activations