INDEX

Explanations

references to military ranks and figures

oai_token-act-pair · gpt-3.5-turbo

mentions of military ranks, specifically "Colonel."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Pengu

-0.75

sett

-0.73

lins

-0.72

irlf

-0.70

itar

-0.69

thora

-0.69

elf

-0.68

robat

-0.66

 Chaser

-0.64

pun

-0.64

POSITIVE LOGITS

 Gaddafi

0.86

LECT

0.85

onel

0.82

terday

0.75

ĸļ

0.75

xual

0.74

agne

0.72

ktop

0.70

ength

0.69

trl

0.68

Activations Density 0.045%

references to military ranks and figures

mentions of military ranks, specifically "Colonel."

No Comments

No Known Activations