INDEX

Explanations

mentions of sudden increases or spikes in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to increases or surges 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 @ 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

ĳ

-0.86

ĪĴ

-0.83

ĻĤ

-0.80

¡

-0.78

vironments

-0.77

¢

-0.76

66666666

-0.75

orate

-0.74

Ł

-0.73

Ĥ

-0.73

POSITIVE LOGITS

 surge

1.00

 surges

0.85

ulic

0.82

 tide

0.79

 tides

0.77

ilight

0.75

 surging

0.72

 Limbaugh

0.71

ulse

0.70

 Surge

0.70

Activations Density 0.024%

mentions of sudden increases or spikes in various contexts

references to increases or surges in various contexts

No Comments

No Known Activations