INDEX

Explanations

proper nouns often related to people or organizations

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or entities, particularly in relation to discussions or events

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

raltar

-0.95

 Pinball

-0.85

swick

-0.85

espie

-0.81

 McAuliffe

-0.81

clips

-0.80

 Gillespie

-0.80

uliffe

-0.79

pty

-0.78

olson

-0.77

POSITIVE LOGITS

Ans

2.00

Ig

1.87

Eb

1.56

soy

1.38

Sag

1.33

 Benson

1.31

Ek

1.24

Soy

1.23

Ish

1.19

Eg

1.15

Activations Density 0.063%

proper nouns often related to people or organizations

references to specific individuals or entities, particularly in relation to discussions or events

No Comments

No Known Activations