INDEX

Explanations

headlines featuring events or incidents

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and their context in sentences

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

reciation

-0.70

authorized

-0.69

itol

-0.67

Seattle

-0.67

ozo

-0.67

EO

-0.66

ivable

-0.66

ulus

-0.66

osing

-0.65

oes

-0.65

POSITIVE LOGITS

 Photograph

0.91

 Dame

0.86

 Pict

0.78

 Ahead

0.78

 Gian

0.76

Hem

0.73

 Irwin

0.73

ï

0.72

Kil

0.72

 Opposition

0.71

Activations Density 0.064%

headlines featuring events or incidents

punctuation marks and their context in sentences

No Comments

No Known Activations