INDEX

Explanations

suggestions or recommendations from text

oai_token-act-pair · gpt-3.5-turbo

expressions of frustration or dissatisfaction

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alter

-0.73

Minor

-0.63

Interview

-0.62

TEXT

-0.61

 Nicarag

-0.58

Moh

-0.58

ivari

-0.57

sth

-0.55

 Wang

-0.55

Rih

-0.55

POSITIVE LOGITS

*/(

0.79

ngth

0.79

apter

0.77

odan

0.73

ELY

0.72

 cheap

0.71

 otherwise

0.71

Ô

0.70

 surely

0.70

eways

0.69

Activations Density 0.680%

suggestions or recommendations from text

expressions of frustration or dissatisfaction

No Comments

No Known Activations