INDEX

Explanations

words related to confirming or affirming statements

oai_token-act-pair · gpt-3.5-turbo

affirmative responses to questions or statements

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

bage

-0.84

perial

-0.70

inese

-0.67

ensis

-0.65

RAW

-0.64

 ILCS

-0.63

 externalToEVAOnly

-0.63

isf

-0.63

enegger

-0.60

leted

-0.59

POSITIVE LOGITS

terday

1.73

sir

0.81

 Means

0.78

ZI

0.74

YES

0.72

eed

0.70

asar

0.67

Mi

0.66

Ã±

0.65

 matter

0.65

Activations Density 0.020%

words related to confirming or affirming statements

affirmative responses to questions or statements

No Comments

No Known Activations