INDEX

Explanations

words related to insults

oai_token-act-pair · gpt-3.5-turbo

instances of the word "insult" and related variations depicting derogatory remarks or disrespectful language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

arijuana

-0.80

ilver

-0.79

enfranch

-0.72

ioch

-0.72

aver

-0.72

ilk

-0.72

negie

-0.71

-0.70

ucket

-0.70

ynthesis

-0.68

POSITIVE LOGITS

 insult

1.30

 insults

1.15

 insulted

1.06

 insulting

1.04

 disrespect

0.97

ingly

0.93

 prejudice

0.88

 humili

0.88

 dispar

0.85

 offend

0.84

Activations Density 0.017%

words related to insults

instances of the word "insult" and related variations depicting derogatory remarks or disrespectful language

No Comments

No Known Activations