INDEX

Explanations

words related to sharp sounds or actions

oai_token-act-pair · gpt-3.5-turbo

words associated with clapping and applause

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

IRE

-0.71

lict

-0.69

 Commons

-0.69

icum

-0.67

ormal

-0.66

ctic

-0.65

perate

-0.65

ignty

-0.64

otype

-0.63

VI

-0.61

POSITIVE LOGITS

sticks

1.07

down

0.98

downs

0.96

dash

0.94

eworthy

0.93

ingly

0.91

stick

0.89

oon

0.85

shots

0.83

ularity

0.81

Activations Density 0.172%

words related to sharp sounds or actions

words associated with clapping and applause

No Comments

No Known Activations