INDEX

Explanations

questions or statements expressing uncertainty

oai_token-act-pair · gpt-3.5-turbo

instances of uncertainty or lack of knowledge in the text

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

izont

-0.76

ishable

-0.72

atism

-0.70

attery

-0.70

coni

-0.70

gencies

-0.67

aez

-0.66

isco

-0.66

otom

-0.64

assi

-0.64

POSITIVE LOGITS

how

0.95

 exactly

0.82

why

0.81

 whether

0.81

 anymore

0.77

how

0.74

 what

0.73

lege

0.71

ledged

0.69

why

0.66

Activations Density 0.043%

questions or statements expressing uncertainty

instances of uncertainty or lack of knowledge in the text

No Comments

No Known Activations