INDEX

Explanations

mentions of specific military and political entities

oai_token-act-pair · gpt-3.5-turbo

references to military or governmental entities and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

luaj

-0.81

ologies

-0.78

 Rowling

-0.76

ocr

-0.76

minecraft

-0.74

 Dickens

-0.73

climate

-0.72

etting

-0.71

nect

-0.71

olkien

-0.71

POSITIVE LOGITS

 troops

1.39

 soldiers

1.35

 helicopters

1.26

 snipers

1.24

 gunfire

1.23

 Forces

1.19

 marines

1.15

 forces

1.14

 troopers

1.11

 patrols

1.09

Activations Density 0.303%

mentions of specific military and political entities

references to military or governmental entities and conflicts

No Comments

No Known Activations