INDEX

Explanations

information sections or articles indicated by the phrase "op-ed" in various contexts or publications

oai_token-act-pair · gpt-3.5-turbo

references to opinion pieces in news articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 GOODMAN

-0.68

ĸļ

-0.65

 unlocking

-0.65

enegger

-0.63

 EntityItem

-0.63

 Awakens

-0.61

 Arabian

-0.61

Zup

-0.61

 Dign

-0.60

beit

-0.59

POSITIVE LOGITS

eds

0.88

editor

0.79

estate

0.79

natal

0.79

Doc

0.79

Ed

0.78

office

0.78

etric

0.77

politics

0.77

comment

0.76

Activations Density 0.026%

information sections or articles indicated by the phrase "op-ed" in various contexts or publications

references to opinion pieces in news articles

No Comments

No Known Activations