INDEX

Explanations

specific mentions of roles played by actors

oai_token-act-pair · gpt-3.5-turbo

references to roles and performances in the context of acting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

-0.88

Statistics

-0.74

TPPStreamerBot

-0.73

 newsletters

-0.69

à¼

-0.69

Operation

-0.68

 Gallup

-0.68

Economic

-0.67

 redist

-0.67

Spread

-0.65

POSITIVE LOGITS

acters

1.07

 actress

1.04

 actresses

1.03

wright

1.01

 actor

0.95

 portraying

0.93

 actors

0.92

 starring

0.90

 audition

0.87

writer

0.87

Activations Density 0.180%

specific mentions of roles played by actors

references to roles and performances in the context of acting

No Comments

No Known Activations