INDEX

Explanations

questions or statements expressing debate or inquiry

oai_token-act-pair · gpt-3.5-turbo

key nouns and their relationships in complex statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

comfort

-0.81

enegger

-0.76

Pic

-0.72

Vers

-0.71

ufact

-0.69

opens

-0.69

Wil

-0.69

ickr

-0.66

laughs

-0.66

Font

-0.64

POSITIVE LOGITS

 differ

0.78

 shine

0.75

 stray

0.67

exist

0.66

 surrog

0.66

 represent

0.64

 mean

0.62

 exist

0.62

 resonate

0.60

 suffice

0.60

Activations Density 0.246%

questions or statements expressing debate or inquiry

key nouns and their relationships in complex statements

No Comments

No Known Activations