INDEX

Explanations

specific locations described in a numerical block format

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic locations or blocks in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

anson

-0.68

Versions

-0.66

oglobin

-0.66

zsche

-0.66

oleon

-0.64

atically

-0.62

emia

-0.62

ipedia

-0.61

eer

-0.60

xon

-0.60

POSITIVE LOGITS

 radius

0.85

aded

0.82

tyard

0.80

yard

0.78

 plaza

0.76

 bounded

0.74

 southwest

0.73

quote

0.73

yards

0.73

 waterfront

0.73

Activations Density 0.016%

specific locations described in a numerical block format

references to specific geographic locations or blocks in texts

No Comments

No Known Activations