INDEX

Explanations

proper names, likely related to news personalities or political figures

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 climax

-0.72

worldly

-0.72

fecture

-0.71

nings

-0.66

 favourites

-0.65

 Jagu

-0.64

 heroine

-0.64

âĶĢâĶĢ

-0.64

 opener

-0.63

ultimate

-0.63

POSITIVE LOGITS

 Blumenthal

0.98

 McCarthy

0.97

 Wasserman

0.94

 McInt

0.93

 Bernstein

0.93

 Schiff

0.92

 McCain

0.91

 Flynn

0.90

 Shapiro

0.90

 Biden

0.88

Activations Density 0.300%

proper names, likely related to news personalities or political figures

proper nouns, particularly names of individuals

No Comments

No Known Activations