INDEX

Explanations

references to the United States (U.S.) and its related entities or actions

oai_token-act-pair · gpt-3.5-turbo

references to the United States government or entities

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

bably

-0.82

 guiActiveUn

-0.71

ebook

-0.69

igs

-0.68

criptions

-0.63

 srfAttach

-0.62

cipled

-0.61

ients

-0.61

byss

-0.60

BOOK

-0.60

POSITIVE LOGITS

 Postal

0.97

 Embassy

0.96

 Geological

0.92

 Navy

0.89

 Agency

0.85

 Treasury

0.85

 Senate

0.85

 Territories

0.84

 embassy

0.84

 Army

0.83

Activations Density 0.087%

references to the United States (U.S.) and its related entities or actions

references to the United States government or entities

No Comments

No Known Activations