INDEX

Explanations

mentions of the word "Wool" along with some associated words

oai_token-act-pair · gpt-3.5-turbo

mentions of "wool" and its variations

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

CENT

-0.77

 Sacrament

-0.68

 Cuomo

-0.68

Oro

-0.67

 citation

-0.65

 Hiroshima

-0.64

 Aval

-0.64

 Clash

-0.63

 Explain

-0.62

POSITIVE LOGITS

wich

1.14

sey

1.00

worth

0.98

nesday

0.97

worms

0.97

sten

0.96

mouth

0.94

awei

0.93

folk

0.90

velength

0.90

Activations Density 0.009%

mentions of the word "Wool" along with some associated words

mentions of "wool" and its variations

No Comments

No Known Activations