INDEX

Explanations

phrases indicating equality, inclusion, and shared experiences

oai_token-act-pair · gpt-3.5-turbo

expressions of collective experiences and opinions

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

qus

-0.76

OGR

-0.72

interstitial

-0.63

 lure

-0.60

ainment

-0.59

 Newsletter

-0.59

 Advertisement

-0.57

stra

-0.56

 Examiner

-0.55

eka

-0.55

POSITIVE LOGITS

 except

1.16

 alike

0.86

except

0.85

 equally

0.83

Tes

0.73

ses

0.70

 imaginable

0.70

 agree

0.67

 individually

0.65

lishes

0.65

Activations Density 0.231%

phrases indicating equality, inclusion, and shared experiences

expressions of collective experiences and opinions

No Comments

No Known Activations