INDEX

Explanations

references to a specific word "Bro"

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the term "Bro" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aneous

-0.70

 Dull

-0.66

 EDITION

-0.65

 Nadu

-0.64

lessly

-0.63

orship

-0.63

lessness

-0.63

URA

-0.63

ORY

-0.61

 Gemini

-0.61

POSITIVE LOGITS

ccoli

1.20

oks

1.07

gue

1.05

dy

1.01

keye

1.00

chet

0.98

thren

0.97

kens

0.97

etooth

0.95

thel

0.95

Activations Density 0.016%

references to a specific word "Bro"

repeated mentions of the term "Bro" in various contexts

No Comments

No Known Activations