INDEX

Explanations

mentions of the tennis player Novak Djokovic

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to places, particularly names of cities or 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

ãĤ¶

-0.80

rette

-0.74

 maid

-0.72

iesta

-0.70

retty

-0.70

jriwal

-0.68

 tempo

-0.66

 ants

-0.66

udging

-0.66

riet

-0.65

POSITIVE LOGITS

Ö¼

0.80

sky

0.71

å£«

0.68

vich

0.65

 Answers

0.64

oway

0.63

 Falls

0.63

 Yanuk

0.63

 Diesel

0.63

 McAuliffe

0.61

Activations Density 0.185%

mentions of the tennis player Novak Djokovic

proper nouns related to places, particularly names of cities or individuals

No Comments

No Known Activations