INDEX

Explanations

mentions of individuals holding editorial positions

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "editor" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pered

-0.79

bley

-0.77

bones

-0.73

pering

-0.73

achi

-0.73

ptoms

-0.71

enegger

-0.68

ulia

-0.67

rises

-0.66

 Territories

-0.66

POSITIVE LOGITS

ials

1.11

ially

1.07

editor

0.85

furt

0.78

ienne

0.74

itatively

0.73

 editor

0.71

 laureate

0.69

 Picks

0.67

iola

0.66

Activations Density 0.016%

mentions of individuals holding editorial positions

mentions of the word "editor" in various contexts

No Comments

No Known Activations