INDEX

Explanations

specific mentions of news channels and frequencies

oai_token-act-pair · gpt-3.5-turbo

references to specific news channels and broadcast formats

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

wikipedia

-0.71

 takeoff

-0.71

 leveling

-0.69

utations

-0.68

blogspot

-0.65

uscript

-0.64

 gmaxwell

-0.64

 seiz

-0.63

wcs

-0.62

 Â¥

-0.61

POSITIVE LOGITS

 Broadcasting

1.04

 Television

0.99

 broadcaster

0.88

 television

0.87

 Productions

0.87

CTV

0.86

 Thrones

0.84

TV

0.84

 airs

0.83

 broadcasts

0.82

Activations Density 0.077%

specific mentions of news channels and frequencies

references to specific news channels and broadcast formats

No Comments

No Known Activations