INDEX

Explanations

proper names, particularly of actors in movie productions

oai_token-act-pair · gpt-3.5-turbo

names of actors and their roles or related contexts in films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Statistics

-0.98

STATE

-0.79

oard

-0.76

Policy

-0.73

 STATS

-0.73

policy

-0.72

minimum

-0.71

usra

-0.71

ntil

-0.70

alyses

-0.70

POSITIVE LOGITS

enegger

1.21

 starring

1.18

 movies

1.15

 audition

1.12

 Actor

1.12

 cinem

1.11

 films

1.10

 starred

1.10

 Actress

1.08

 actress

1.08

Activations Density 0.227%

proper names, particularly of actors in movie productions

names of actors and their roles or related contexts in films

No Comments

No Known Activations