INDEX

Explanations

phrases indicating initial thoughts or actions

oai_token-act-pair · gpt-3.5-turbo

statements that express initial thoughts or impressions

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

etheless

-0.83

contin

-0.78

sports

-0.70

verend

-0.68

arians

-0.68

 notwithstanding

-0.66

interrupted

-0.65

ichever

-0.64

mble

-0.64

 therein

-0.63

POSITIVE LOGITS

 introdu

0.85

 glance

0.70

aceae

0.66

 hitch

0.66

0.65

 whiff

0.63

 sensation

0.62

ITNESS

0.62

 introduction

0.62

buquerque

0.61

Activations Density 0.428%

phrases indicating initial thoughts or actions

statements that express initial thoughts or impressions

No Comments

No Known Activations