INDEX

Explanations

profanity and offensive words

oai_token-act-pair · gpt-3.5-turbo

explicit language and strong expletives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

utterstock

-0.78

 guiActiveUnfocused

-0.72

 guiActiveUn

-0.71

 ancest

-0.70

 surn

-0.69

OSP

-0.69

 docking

-0.67

 showc

-0.66

Vert

-0.66

 rece

-0.66

POSITIVE LOGITS

nuts

0.84

cr

0.83

bah

0.82

shit

0.81

heads

0.80

fuck

0.77

peat

0.75

 nuts

0.75

dust

0.75

holes

0.75

Activations Density 0.021%

profanity and offensive words

explicit language and strong expletives

No Comments

No Known Activations