INDEX

Explanations

words related to surnames or names

oai_token-act-pair · gpt-3.5-turbo

mentions of characters or names associated with the word "cock."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 GOODMAN

-0.73

PsyNetMessage

-0.69

 Grateful

-0.68

 Blessed

-0.66

 Serbian

-0.65

 Serbia

-0.63

UGE

-0.63

 Kosovo

-0.62

 stair

-0.62

 Canaver

-0.61

POSITIVE LOGITS

cock

1.26

roach

1.11

tails

1.04

pit

1.00

tail

0.99

mong

0.96

oons

0.95

haw

0.91

rod

0.91

lear

0.91

Activations Density 0.010%

words related to surnames or names

mentions of characters or names associated with the word "cock."

No Comments

No Known Activations