INDEX

Explanations

words related to clothing items, particularly t-shirts

oai_token-act-pair · gpt-3.5-turbo

mentions of T-shirts or related clothing items, particularly those with branding or names

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

izoph

-0.76

omnia

-0.73

minist

-0.70

 ILCS

-0.69

technology

-0.68

inqu

-0.66

INESS

-0.66

pict

-0.66

urg

-0.64

phia

-0.63

POSITIVE LOGITS

tee

1.13

pee

1.05

pees

0.89

chery

0.85

Tee

0.76

Ã±o

0.71

 clearance

0.70

 jumper

0.70

baugh

0.70

 Ryder

0.68

Activations Density 0.022%

words related to clothing items, particularly t-shirts

mentions of T-shirts or related clothing items, particularly those with branding or names

No Comments

No Known Activations