INDEX

Explanations

mentions of economic or political sanctions

oai_token-act-pair · gpt-3.5-turbo

references to sanctions

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

WORK

-0.96

ITNESS

-0.83

ership

-0.82

ergy

-0.79

edes

-0.79

rx

-0.79

OTE

-0.76

rote

-0.72

swick

-0.72

ways

-0.71

POSITIVE LOGITS

 sanctions

1.46

 sanction

1.16

 embargo

1.07

 imposed

0.93

 levied

0.91

 deterrent

0.90

 deterrence

0.89

 coerc

0.89

 relief

0.86

ategory

0.86

Activations Density 0.012%

mentions of economic or political sanctions

references to sanctions

No Comments

No Known Activations