INDEX

Explanations

political figures and organizations

oai_token-act-pair · gpt-3.5-turbo

names of people and organizations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enment

-0.58

 Debor

-0.53

 denomin

-0.52

agher

-0.51

 attest

-0.51

wealth

-0.51

 toile

-0.48

 sugg

-0.48

.$

-0.46

cms

-0.45

POSITIVE LOGITS

atism

0.54

cheat

0.49

ropri

0.48

ahu

0.47

acial

0.47

seless

0.47

 shouldn

0.46

 should

0.46

hematically

0.45

bably

0.45

Activations Density 1.208%

political figures and organizations

names of people and organizations

No Comments

No Known Activations