INDEX

Explanations

mentions or discussions about the media

oai_token-act-pair · gpt-3.5-turbo

mentions of the media and its influence or portrayal 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ta

-0.73

erville

-0.71

owsky

-0.68

combe

-0.67

sql

-0.67

vasive

-0.66

Phi

-0.66

Pis

-0.65

ranged

-0.63

0000000000000000

-0.63

POSITIVE LOGITS

eval

1.44

 outlets

1.24

 outlet

1.07

 coverage

0.97

 pundits

0.91

mog

0.90

 blackout

0.88

 circus

0.86

verage

0.85

 mogul

0.85

Activations Density 0.042%

mentions or discussions about the media

mentions of the media and its influence or portrayal in various contexts

No Comments

No Known Activations