INDEX

Explanations

locations or places mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or contexts within a narrative

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

DragonMagazine

-0.93

xual

-0.84

oeuv

-0.82

âĤ¬

-0.79

Ãį

-0.78

 realised

-0.75

 learnt

-0.75

Firstly

-0.74

Euro

-0.74

Series

-0.73

POSITIVE LOGITS

 Louisiana

1.53

 Baton

1.53

 Ohio

1.51

 Alabama

1.51

 Wisconsin

1.50

 Maryland

1.49

 Arkansas

1.49

 Texas

1.49

 Nebraska

1.48

 Tennessee

1.48

Activations Density 0.318%

locations or places mentioned in news articles

references to specific locations or contexts within a narrative

No Comments

No Known Activations