INDEX

Explanations

movie titles and actors' names

oai_token-act-pair · gpt-3.5-turbo

mentions of actors and their roles in films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

foundation

-0.87

nai

-0.79

veland

-0.77

£ı

-0.73

inventoryQuantity

-0.69

tsy

-0.68

ĵĺ

-0.68

-0.67

ascus

-0.67

pex

-0.66

POSITIVE LOGITS

leck

0.98

 starring

0.95

 actresses

0.80

 actress

0.76

eele

0.76

 stars

0.74

 Natalie

0.74

eaturing

0.70

 singers

0.70

 Chloe

0.69

Activations Density 0.043%

movie titles and actors' names

mentions of actors and their roles in films

No Comments

No Known Activations