INDEX

Explanations

explicit uses of the word "shit" in the text

oai_token-act-pair · gpt-3.5-turbo

expressions of frustration or disdain

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

HCR

-0.84

AUT

-0.78

gary

-0.71

fman

-0.71

================================

-0.68

————————————————

-0.65

icable

-0.65

eur

-0.62

Green

-0.62

Scient

-0.62

POSITIVE LOGITS

shit

1.00

bags

0.95

dump

0.91

loads

0.85

 shit

0.84

shots

0.84

 heap

0.83

 Shit

0.78

fuck

0.78

 crap

0.77

Activations Density 0.007%

explicit uses of the word "shit" in the text

expressions of frustration or disdain

No Comments

No Known Activations