INDEX

Explanations

words related to threatening behavior

oai_token-act-pair · gpt-3.5-turbo

phrases related to threats, particularly those of violence or intimidation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

çĦ

-0.84

arist

-0.80

urgy

-0.73

coat

-0.71

puted

-0.71

mys

-0.70

 Balanced

-0.70

bits

-0.69

cise

-0.69

éĸ

-0.68

POSITIVE LOGITS

 threats

0.85

 posed

0.81

 warnings

0.80

 threatening

0.78

 posters

0.75

 threat

0.74

 intimidation

0.74

 hotline

0.74

 threatened

0.73

 leveled

0.72

Activations Density 0.023%

words related to threatening behavior

phrases related to threats, particularly those of violence or intimidation

No Comments

No Known Activations