INDEX

Explanations

phrases related to instructions or actions the reader should take

oai_token-act-pair · gpt-3.5-turbo

the word "that" and its various uses throughout the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Ire

-0.61

Fax

-0.60

Desk

-0.58

bledon

-0.57

Guard

-0.56

 Coordinator

-0.55

erenn

-0.53

æµ

-0.51

Eth

-0.51

æĿ

-0.51

POSITIVE LOGITS

esson

0.81

lav

0.70

 violates

0.66

 mattered

0.63

 includes

0.62

 fateful

0.62

 pesky

0.61

advertisement

0.60

 accompanies

0.59

 Pastebin

0.59

Activations Density 0.261%

phrases related to instructions or actions the reader should take

the word "that" and its various uses throughout the document

No Comments

No Known Activations