INDEX

Explanations

concepts related to threats and intimidation

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "threat."

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

Not in Any Lists

No Comments

Negative Logits

mys

-0.91

ilts

-0.82

algia

-0.81

val

-0.81

iked

-0.77

urgy

-0.76

cle

-0.74

ann

-0.71

rain

-0.71

gart

-0.70

POSITIVE LOGITS

 threaten

1.13

 threatens

1.11

 threats

0.98

 endanger

0.94

 threatened

0.92

 threatening

0.91

 challeng

0.91

 Threat

0.91

threat

0.90

 menacing

0.85

Activations Density 0.006%

concepts related to threats and intimidation

references to the concept of "threat."

No Comments

No Known Activations