INDEX

Explanations

mentions of the media

oai_token-act-pair · gpt-3.5-turbo

mentions of "media" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

vasive

-0.78

adian

-0.73

erville

-0.72

 Reson

-0.71

cker

-0.68

 Parenthood

-0.67

ktop

-0.66

Tec

-0.65

abouts

-0.65

php

-0.64

POSITIVE LOGITS

eval

1.18

 outlets

1.16

 outlet

1.02

mog

0.86

 literacy

0.85

 coverage

0.83

 pundits

0.83

 circus

0.82

 plurality

0.82

 broadcasters

0.82

Activations Density 0.027%

mentions of the media

mentions of "media" in various contexts

No Comments

No Known Activations