INDEX

Explanations

questions or actions related to various processes or decisions

oai_token-act-pair · gpt-3.5-turbo

inquiries or questions on how to perform tasks or actions

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

redd

-0.72

bda

-0.66

axter

-0.64

Ĺ

-0.63

dra

-0.62

bryce

-0.60

tex

-0.59

 entirety

-0.58

runs

-0.57

krit

-0.57

POSITIVE LOGITS

uate

0.89

 yourself

0.75

itably

0.71

lessly

0.68

 these

0.67

 this

0.67

 them

0.66

 your

0.65

 efficiently

0.65

ulate

0.64

Activations Density 0.222%

questions or actions related to various processes or decisions

inquiries or questions on how to perform tasks or actions

No Comments

No Known Activations