INDEX

Explanations

words related to desires or wants

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'w'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 bloom

-0.67

uate

-0.66

Duo

-0.65

tem

-0.64

ŃĶ

-0.63

 inhibition

-0.63

 semin

-0.63

 plaintiff

-0.62

 unpre

-0.61

 confessions

-0.61

POSITIVE LOGITS

isdom

1.44

elcome

1.43

itness

1.40

orship

1.40

idespread

1.39

orry

1.36

ield

1.36

ielding

1.35

anted

1.33

restling

1.32

Activations Density 0.031%

words related to desires or wants

occurrences of the letter 'w'

No Comments

No Known Activations