INDEX

Explanations

word sequences that represent the structure of a letter

oai_token-act-pair · gpt-3.5-turbo

references to letters and written correspondence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 booths

-0.82

Course

-0.76

 documentaries

-0.75

¥µ

-0.72

Stage

-0.72

oggles

-0.72

 exhibitions

-0.72

Plex

-0.69

"},"

-0.68

 Races

-0.67

POSITIVE LOGITS

 letter

1.76

 letters

1.46

 dated

1.44

 handwritten

1.39

Dear

1.38

letter

1.36

 forwarded

1.33

 mailed

1.32

 Letter

1.29

 correspondence

1.28

Activations Density 0.311%

word sequences that represent the structure of a letter

references to letters and written correspondence

No Comments

No Known Activations