INDEX

Explanations

headings or sections within a document

oai_token-act-pair · gpt-3.5-turbo

instances of numerical data or statistics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 life

-0.61

 XIII

-0.60

 antit

-0.60

 Breed

-0.59

 adversaries

-0.58

 Cycle

-0.58

 Leilan

-0.57

 Cent

-0.57

 VIII

-0.57

 Trident

-0.57

POSITIVE LOGITS

posted

0.86

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.75

inducing

0.73

selves

0.72

é»Ĵ

0.72

ÂłÂłÂł

0.71

multipl

0.70

hazard

0.70

except

0.70

âĹ¼

0.69

Activations Density 0.229%

headings or sections within a document

instances of numerical data or statistics

No Comments

No Known Activations