INDEX

Explanations

phrases indicating solidarity or shared experience

oai_token-act-pair · gpt-3.5-turbo

expressions indicating the concept of solitude or being alone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Skydragon

-0.83

abase

-0.68

techn

-0.66

imum

-0.63

wash

-0.63

ibal

-0.62

thinkable

-0.61

 Junk

-0.59

iet

-0.59

boats

-0.59

POSITIVE LOGITS

 Canaver

0.80

 accus

0.76

 anymore

0.71

Lens

0.70

zek

0.68

nor

0.68

 Rico

0.64

oshenko

0.64

 Somers

0.64

coni

0.62

Activations Density 0.070%

phrases indicating solidarity or shared experience

expressions indicating the concept of solitude or being alone

No Comments

No Known Activations