INDEX

Explanations

proper nouns related to people and places

oai_token-act-pair · gpt-3.5-turbo

references to specific people, places, and recognized achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Tokens

-0.56

 cohesion

-0.52

IPM

-0.52

 conventions

-0.51

 inputs

-0.51

 dissatisf

-0.51

Zot

-0.50

 shenan

-0.50

 iPads

-0.49

 VIEW

-0.49

POSITIVE LOGITS

agonist

0.75

utenant

0.71

appointed

0.66

assador

0.66

atcher

0.65

 dancer

0.63

 inmate

0.63

 lover

0.62

apper

0.62

trained

0.61

Activations Density 0.683%

proper nouns related to people and places

references to specific people, places, and recognized achievements

No Comments

No Known Activations