INDEX

Explanations

mentions of professional actors

oai_token-act-pair · gpt-3.5-turbo

references to actors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

£ı

-0.72

wart

-0.69

rontal

-0.68

xit

-0.68

fty

-0.67

theless

-0.64

etheless

-0.64

yip

-0.62

Operation

-0.60

ģ«

-0.60

POSITIVE LOGITS

 portraying

1.17

 audition

0.84

rities

0.83

 starring

0.82

 actor

0.82

 portray

0.80

 Natalie

0.77

 portrays

0.77

 actress

0.75

Db

0.74

Activations Density 0.037%

mentions of professional actors

references to actors in various contexts

No Comments

No Known Activations