INDEX

Explanations

keywords related to the streaming platform "Netflix."

oai_token-act-pair · gpt-3.5-turbo

mentions of the streaming service Netflix

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

manuel

-0.86

uate

-0.72

rists

-0.71

imer

-0.67

orically

-0.66

cised

-0.66

rique

-0.66

tera

-0.64

 bicy

-0.63

ften

-0.63

POSITIVE LOGITS

 Streaming

0.84

Netflix

0.83

Film

0.82

 Orig

0.81

 Studios

0.77

 Observatory

0.76

wik

0.75

 Netflix

0.75

iture

0.73

Girls

0.73

Activations Density 0.014%

keywords related to the streaming platform "Netflix."

mentions of the streaming service Netflix

No Comments

No Known Activations