INDEX

Explanations

instances where someone or something is appearing in a specific context

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "appear" and its variations, particularly in legal or media contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

icz

-0.76

Â·Â·

-0.69

 handled

-0.67

 maintains

-0.66

hesda

-0.66

ystem

-0.64

ties

-0.63

 prefers

-0.62

 ensued

-0.62

 accommod

-0.62

POSITIVE LOGITS

 advertisements

0.92

 commercials

0.86

 silhouette

0.80

 screenshots

0.79

 doorway

0.79

 headlines

0.78

Picture

0.77

 photographs

0.76

 billboards

0.74

ads

0.74

Activations Density 0.216%

instances where someone or something is appearing in a specific context

occurrences of the word "appear" and its variations, particularly in legal or media contexts

No Comments

No Known Activations