INDEX

Explanations

information related to following specific steps or instructions

oai_token-act-pair · gpt-3.5-turbo

introductory phrases or elements that emphasize a sequence or structure in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

arat

-0.69

orrow

-0.67

lees

-0.66

cffff

-0.62

Later

-0.62

sports

-0.62

etheless

-0.60

later

-0.60

monary

-0.59

leanor

-0.59

POSITIVE LOGITS

 introdu

0.71

 obligatory

0.66

 unaccompanied

0.63

 basics

0.62

 introduction

0.61

 disclaimer

0.59

rontal

0.59

 overview

0.58

ÂłÂłÂłÂł

0.58

asma

0.58

Activations Density 0.453%

information related to following specific steps or instructions

introductory phrases or elements that emphasize a sequence or structure in writing

No Comments

No Known Activations