INDEX

Explanations

phrases related to roosters

oai_token-act-pair · gpt-3.5-turbo

instances of the word "cock" and its variants used 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 @ 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

DragonMagazine

-0.72

éĹĺ

-0.71

PsyNetMessage

-0.69

 psychiat

-0.66

 Palestin

-0.65

 GOODMAN

-0.65

 kcal

-0.64

è£ħ

-0.64

 publicity

-0.63

VK

-0.63

POSITIVE LOGITS

roach

1.61

pit

1.20

crow

1.10

tail

1.09

haw

1.06

mong

1.00

tails

1.00

pool

0.96

pots

0.95

hawk

0.92

Activations Density 0.015%

phrases related to roosters

instances of the word "cock" and its variants used in various contexts

No Comments

No Known Activations