INDEX

Explanations

numbers related to statistics or measurements

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a percentage or quantitative change

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

 largeDownload

-0.78

ational

-0.77

>[

-0.73

itled

-0.72

 succeeded

-0.71

marked

-0.70

ivia

-0.69

hid

-0.67

 succeeds

-0.67

ouse

-0.66

POSITIVE LOGITS

 virtue

1.06

0.88

 fiat

0.88

 leaps

0.85

0.84

 multiplying

0.81

 eliminating

0.72

products

0.71

 chopping

0.69

Activations Density 0.092%

numbers related to statistics or measurements

phrases indicating a percentage or quantitative change

No Comments

No Known Activations