INDEX

Explanations

verbs or phrases related to subjecting or exposing someone to something, often with negative connotations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating subjection or external influence on individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

case

-0.73

bra

-0.72

soon

-0.66

fox

-0.66

ppa

-0.65

yssey

-0.65

iola

-0.63

cube

-0.63

 headlined

-0.63

framework

-0.62

POSITIVE LOGITS

 certain

0.90

 whichever

0.79

 these

0.77

the

0.77

 various

0.76

 whatever

0.74

0.73

an

0.73

 varying

0.72

 stereotypical

0.72

Activations Density 0.231%

verbs or phrases related to subjecting or exposing someone to something, often with negative connotations

phrases indicating subjection or external influence on individuals

No Comments

No Known Activations