INDEX

Explanations

mentions of specific entities or locations followed by the word "Zone."

oai_token-act-pair · gpt-3.5-turbo

mentions of "Zone" in various contexts

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

achus

-0.78

clud

-0.73

asio

-0.72

LECT

-0.70

cffff

-0.68

oneliness

-0.67

unin

-0.66

dom

-0.66

rawdownloadcloneembedreportprint

-0.65

 mathemat

-0.64

POSITIVE LOGITS

Zone

0.82

anza

0.62

 reversed

0.62

 Pact

0.61

 carrots

0.60

 aviation

0.60

td

0.59

 Aviation

0.59

 gone

0.58

 pilots

0.58

Activations Density 0.001%

mentions of specific entities or locations followed by the word "Zone."

mentions of "Zone" in various contexts

No Comments

No Known Activations