INDEX

Explanations

phrases related to inappropriate actions or behavior

oai_token-act-pair · gpt-3.5-turbo

instances of the word "inappropriate" and related contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ership

-0.86

iph

-0.86

stone

-0.83

rix

-0.82

glass

-0.82

abiding

-0.79

board

-0.77

neys

-0.75

eely

-0.74

ingen

-0.74

POSITIVE LOGITS

 inappropriate

1.16

 improper

0.96

 undermin

0.85

 inappropriately

0.84

 misuse

0.81

 indecent

0.80

 improperly

0.79

 concess

0.77

 interfered

0.77

 mishand

0.77

Activations Density 0.012%

phrases related to inappropriate actions or behavior

instances of the word "inappropriate" and related contexts

No Known Activations