INDEX

Explanations

phrases related to news and media coverage

oai_token-act-pair · gpt-3.5-turbo

instances of state-controlled media mentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

otin

-1.16

etsy

-0.87

benefit

-0.78

 Benson

-0.75

 Cary

-0.74

 Carson

-0.71

weed

-0.70

 Lyme

-0.70

roo

-0.68

 Hawth

-0.68

POSITIVE LOGITS

 quoting

0.92

 quoted

0.92

aganda

0.89

 translated

0.86

 correspondent

0.84

Ä

0.83

 Azerbai

0.81

YPG

0.80

 Jazeera

0.79

ibi

0.77

Activations Density 0.261%

phrases related to news and media coverage

instances of state-controlled media mentions

No Comments

No Known Activations