INDEX

Explanations

mentions of specific roles or characters in the context of casting decisions for actors

oai_token-act-pair · gpt-3.5-turbo

references to roles and casting in acting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

£ı

-0.90

sonian

-0.81

vier

-0.80

 newsletters

-0.74

ensable

-0.72

arta

-0.69

 CrossRef

-0.68

Weather

-0.68

usra

-0.67

 Gallup

-0.67

POSITIVE LOGITS

 portraying

0.93

acters

0.92

 actors

0.90

 actor

0.89

 Judd

0.88

 actresses

0.87

 actress

0.87

 heroine

0.84

 Characters

0.83

 portrayal

0.81

Activations Density 0.168%

mentions of specific roles or characters in the context of casting decisions for actors

references to roles and casting in acting

No Comments

No Known Activations