INDEX

Explanations

phrases describing beliefs, understandings, or statements about individuals or situations

oai_token-act-pair · gpt-3.5-turbo

statements regarding assertions or beliefs about individuals or events

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

 Submission

-0.61

heid

-0.60

Interstitial

-0.59

comes

-0.59

ajo

-0.59

ment

-0.58

 Cancer

-0.58

ettlement

-0.57

avier

-0.56

 monkeys

-0.56

POSITIVE LOGITS

ª

0.79

 proport

0.75

ocry

0.69

 anecd

0.66

¯

0.66

¶

0.64

¬

0.64

 distingu

0.63

 acknowled

0.63

ĳå£«

0.63

Activations Density 0.105%

phrases describing beliefs, understandings, or statements about individuals or situations

statements regarding assertions or beliefs about individuals or events

No Comments

No Known Activations