INDEX

Explanations

references to the media

oai_token-act-pair · gpt-3.5-turbo

mentions of the media and its portrayal in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

vasive

-0.78

erville

-0.77

owsky

-0.69

compatible

-0.68

ta

-0.67

Pis

-0.66

 Nato

-0.65

nance

-0.65

acterial

-0.65

adian

-0.65

POSITIVE LOGITS

 outlets

1.19

eval

1.15

 outlet

1.01

 pundits

0.87

mog

0.86

 circus

0.85

 blackout

0.83

 coverage

0.82

 plurality

0.82

 broadcasters

0.81

Activations Density 0.037%

references to the media

mentions of the media and its portrayal in discussions

No Comments

No Known Activations