INDEX

Explanations

phrases indicating a sequence of events

oai_token-act-pair · gpt-3.5-turbo

instances of personal experiences or realizations

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

making

-0.64

 attire

-0.60

 essentials

-0.60

wear

-0.59

MPG

-0.58

worth

-0.58

 Maxim

-0.58

 Gram

-0.57

 mosquito

-0.57

 essential

-0.57

POSITIVE LOGITS

 recons

0.95

Äį

0.79

 guiActiveUn

0.76

eln

0.74

veyard

0.70

 conclud

0.69

Ï

0.68

DragonMagazine

0.68

adan

0.68

ramids

0.67

Activations Density 0.163%

phrases indicating a sequence of events

instances of personal experiences or realizations

No Comments

No Known Activations