INDEX

Explanations

references to security, technology, and politics

oai_token-act-pair · gpt-3.5-turbo

topics related to political decisions and actions affecting security and trade

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

lag

-0.61

 FranÃ§

-0.59

usercontent

-0.58

Contents

-0.57

nce

-0.56

 Paste

-0.55

".

-0.54

âĢİ

-0.54

olean

-0.54

 ISBN

-0.53

POSITIVE LOGITS

 Kavanaugh

0.71

 Dems

0.71

 tariffs

0.67

 opioids

0.65

 Pelosi

0.64

 Mattis

0.62

 memos

0.61

«ĺ

0.61

%]

0.60

 lobbyists

0.59

Activations Density 0.050%

references to security, technology, and politics

topics related to political decisions and actions affecting security and trade

No Comments

No Known Activations