INDEX

Explanations

references to tall structures like towers

oai_token-act-pair · gpt-3.5-turbo

references to towers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

dit

-0.82

é»Ĵ

-0.71

ties

-0.67

ãĤ±

-0.66

DIT

-0.65

 Luther

-0.65

iotic

-0.64

sweet

-0.63

ters

-0.63

ktop

-0.62

POSITIVE LOGITS

 towers

1.09

 skysc

1.04

 tower

1.00

tower

0.97

 Towers

0.94

 erected

0.92

 heights

0.90

 crane

0.89

raper

0.88

sonian

0.86

Activations Density 0.065%

references to tall structures like towers

references to towers

No Comments

No Known Activations