INDEX

Explanations

proper nouns and names, possibly related to news, photography, and legal issues

oai_token-act-pair · gpt-3.5-turbo

specific names, entities, or significant terms 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TY

-0.86

TY

-0.83

 Strongh

-0.74

Yo

-0.72

ty

-0.70

 TODAY

-0.69

 Tree

-0.68

 Teen

-0.68

Lay

-0.68

 Frankie

-0.67

POSITIVE LOGITS

irc

0.97

av

0.96

irs

0.89

ibr

0.88

uci

0.86

ibia

0.83

ir

0.82

asp

0.82

irl

0.82

kov

0.82

Activations Density 0.392%

proper nouns and names, possibly related to news, photography, and legal issues

specific names, entities, or significant terms in the text

No Comments

No Known Activations