INDEX

Explanations

words related to moral judgment or assessment of situations

oai_token-act-pair · gpt-3.5-turbo

positive or whimsical concepts and themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

emale

-0.67

ilaterally

-0.66

pheus

-0.64

edo

-0.62

æµ

-0.60

Interstitial

-0.59

alore

-0.54

mobi

-0.54

ãĥĩãĤ£

-0.53

 horizont

-0.53

POSITIVE LOGITS

 Coverage

0.54

lement

0.53

BILITIES

0.52

 âĢº

0.51

CRIPTION

0.50

ANS

0.49

NetMessage

0.48

quickShipAvailable

0.48

CVE

0.46

zbollah

0.46

Activations Density 0.901%

words related to moral judgment or assessment of situations

positive or whimsical concepts and themes

No Comments

No Known Activations