INDEX

Explanations

words related to clothing items, specifically shirts

oai_token-act-pair · gpt-3.5-turbo

references to T-shirts or phrases related to T-shirts

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

elsen

-0.77

ruciating

-0.66

 trib

-0.65

ntil

-0.65

ENC

-0.62

iciary

-0.60

 pregn

-0.59

judicial

-0.59

 terrestrial

-0.59

 witness

-0.59

POSITIVE LOGITS

shirt

1.27

shirts

1.15

hirt

1.00

 shirts

0.99

boy

0.98

leeve

0.94

idas

0.91

 sleeve

0.87

 shirt

0.86

boys

0.86

Activations Density 0.009%

words related to clothing items, specifically shirts

references to T-shirts or phrases related to T-shirts

No Comments

No Known Activations