INDEX

Explanations

explicit and potentially offensive language

oai_token-act-pair · gpt-3.5-turbo

expressions of strong profanity or expletives

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

NetMessage

-0.80

BIL

-0.73

ItemThumbnailImage

-0.66

PsyNetMessage

-0.65

 conclud

-0.65

 membr

-0.64

HCR

-0.64

 renewal

-0.63

 rece

-0.63

rouse

-0.62

POSITIVE LOGITS

holes

1.15

hole

1.10

lord

0.95

bags

0.92

fuck

0.91

buster

0.89

nuts

0.85

wit

0.85

glers

0.85

dump

0.84

Activations Density 0.014%

explicit and potentially offensive language

expressions of strong profanity or expletives

No Comments

No Known Activations