INDEX

Explanations

mentions of the word "Bro" followed by a number

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Bro."

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

aneous

-0.67

ãĥ¼ãĥĨãĤ£

-0.67

 Nadu

-0.66

URA

-0.65

 EDITION

-0.65

orship

-0.64

 Mali

-0.63

lessly

-0.63

lessness

-0.62

 lockout

-0.61

POSITIVE LOGITS

ccoli

1.15

oks

1.09

dy

0.99

kens

0.97

keye

0.96

etooth

0.96

thren

0.95

gue

0.92

keley

0.92

chet

0.90

Activations Density 0.012%

mentions of the word "Bro" followed by a number

occurrences of the name "Bro."

No Comments

No Known Activations