INDEX

Explanations

mentions of actors in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to actors and their roles or performances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

PRESS

-0.68

UTERS

-0.67

 Territories

-0.65

yx

-0.62

£ı

-0.59

ggies

-0.59

fty

-0.59

Peg

-0.58

ãĥ¼ãĥ³

-0.58

 Truth

-0.58

POSITIVE LOGITS

 actors

1.23

rities

1.06

 actor

1.06

writers

0.96

 actresses

0.92

 Actor

0.87

Actor

0.85

acters

0.83

 singers

0.81

 actress

0.80

Activations Density 0.008%

mentions of actors in various contexts

references to actors and their roles or performances

No Comments

No Known Activations