INDEX

Explanations

descriptions or mentions of cold temperatures

oai_token-act-pair · gpt-3.5-turbo

references to cold temperatures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Companies

-0.85

UNCH

-0.80

ORTS

-0.79

ICLE

-0.77

bourg

-0.76

anan

-0.74

Bar

-0.73

iage

-0.73

udo

-0.72

IX

-0.70

POSITIVE LOGITS

 cold

1.17

 chill

1.03

cold

1.01

 colder

0.99

 winter

0.91

 sleeper

0.87

 sore

0.87

 snowy

0.87

 winters

0.86

 cooled

0.85

Activations Density 0.010%

descriptions or mentions of cold temperatures

references to cold temperatures

No Comments

No Known Activations