INDEX

Explanations

phrases indicating evaluation, such as "bad" or "difficult"

oai_token-act-pair · gpt-3.5-turbo

phrases expressing difficulty or negative evaluations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ½

-0.75

urd

-0.71

Offline

-0.68

gypt

-0.67

yth

-0.67

ystem

-0.65

last

-0.64

tv

-0.64

iHUD

-0.63

wake

-0.63

POSITIVE LOGITS

agher

0.73

nels

0.66

 Carbuncle

0.66

 elbows

0.65

 harass

0.64

 slicing

0.63

 cruising

0.62

 temptation

0.62

 flavors

0.59

 elbow

0.58

Activations Density 0.127%

phrases indicating evaluation, such as "bad" or "difficult"

phrases expressing difficulty or negative evaluations

No Comments

No Known Activations