INDEX

Explanations

phrases expressing caution or warning

oai_token-act-pair · gpt-3.5-turbo

assertions or statements indicating that ability does not imply permission or appropriateness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 throats

-0.83

 bombed

-0.68

izen

-0.66

ebted

-0.64

 matured

-0.63

ione

-0.62

 specialize

-0.60

 targets

-0.59

 maneu

-0.59

ults

-0.59

POSITIVE LOGITS

soType

0.96

 disqual

0.92

etheless

0.80

 entit

0.79

 preclude

0.79

 negate

0.73

 imply

0.73

 means

0.72

Cause

0.70

advertising

0.70

Activations Density 0.169%

phrases expressing caution or warning

assertions or statements indicating that ability does not imply permission or appropriateness

No Comments

No Known Activations