INDEX

Explanations

references to AK-47 rifles

oai_token-act-pair · gpt-3.5-turbo

mentions of the AK-47 assault rifle

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãĤ£

-0.77

ãĤ§

-0.76

 Vaugh

-0.74

nces

-0.73

 guiActiveUnfocused

-0.72

 istg

-0.71

âĢ¢âĢ¢âĢ¢âĢ¢

-0.71

advertisement

-0.70

 Kepler

-0.70

issance

-0.70

POSITIVE LOGITS

AZ

0.82

AK

0.80

istani

0.79

atana

0.79

AK

0.74

iy

0.72

unta

0.72

ansas

0.71

DEN

0.69

rew

0.68

Activations Density 0.005%

references to AK-47 rifles

mentions of the AK-47 assault rifle

No Comments

No Known Activations