INDEX

Explanations

quotations attributed to certain people, typically authors or journalists

oai_token-act-pair · gpt-3.5-turbo

instances of the word "writes" indicating attribution or quoting of authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

illon

-0.78

eger

-0.70

negie

-0.68

alo

-0.67

illions

-0.67

Ĭ±

-0.66

angular

-0.64

pled

-0.64

ypes

-0.64

Unity

-0.64

POSITIVE LOGITS

writer

0.77

 poems

0.77

ynthesis

0.73

 Journals

0.72

 penned

0.71

books

0.71

 ABOUT

0.69

ipel

0.68

 reprinted

0.68

 poem

0.68

Activations Density 0.031%

quotations attributed to certain people, typically authors or journalists

instances of the word "writes" indicating attribution or quoting of authors

No Comments

No Known Activations