INDEX

Explanations

actions related to prevention or prohibition

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate prevention or avoidance of certain actions or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ratulations

-0.87

quote

-0.75

rongh

-0.74

 partName

-0.73

isode

-0.72

mask

-0.72

starter

-0.70

ios

-0.70

width

-0.70

hai

-0.69

POSITIVE LOGITS

 afar

1.29

 whence

1.09

 thence

1.00

 scratch

0.98

 anywhere

0.86

 inside

0.84

 abroad

0.84

 Brune

0.79

 elsewhere

0.77

 wherever

0.76

Activations Density 0.208%

actions related to prevention or prohibition

phrases that indicate prevention or avoidance of certain actions or conditions

No Comments

No Known Activations