INDEX

Explanations

images or photos mentioned in a document

oai_token-act-pair · gpt-3.5-turbo

mentions of emotional states or reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aterasu

-0.72

hement

-0.67

#$

-0.67

sic

-0.66

oway

-0.65

staking

-0.64

heit

-0.63

rand

-0.60

aturdays

-0.58

 fors

-0.56

POSITIVE LOGITS

Balt

0.62

endra

0.60

misc

0.57

STR

0.57

 Shutterstock

0.55

 Conway

0.54

 Swordsman

0.54

 ILCS

0.54

 playback

0.54

Anonymous

0.54

Activations Density 0.052%

images or photos mentioned in a document

mentions of emotional states or reactions

No Comments

No Known Activations