INDEX

Explanations

instances of the word "brows" with variations in spelling

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 merc

-0.70

Art

-0.66

 authentic

-0.63

 precedent

-0.62

 mono

-0.62

 merit

-0.62

 autonomy

-0.61

 vind

-0.61

 Nero

-0.60

 Tycoon

-0.60

POSITIVE LOGITS

rows

4.81

row

2.77

rowing

2.20

rower

1.80

rown

1.77

rew

1.23

 rows

1.21

ows

1.21

OWS

1.17

column

1.09

Activations Density 0.007%

instances of the word "brows" with variations in spelling

references to specific individuals or entities

No Comments

No Known Activations