INDEX

Explanations

phrases or clauses that express causality

oai_token-act-pair · gpt-3.5-turbo

references to reasons and justifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Enlarge

-0.51

 UNITED

-0.46

BuyableInstoreAndOnline

-0.45

 Belfast

-0.42

iage

-0.42

å£«

-0.40

 Colombian

-0.40

 laun

-0.40

ITIES

-0.40

interstitial

-0.39

POSITIVE LOGITS

esides

0.49

 luck

0.49

 disclaim

0.46

versely

0.46

 spite

0.45

elo

0.45

asty

0.44

 guessed

0.43

 paraph

0.43

alle

0.42

Activations Density 3.727%

phrases or clauses that express causality

references to reasons and justifications

No Comments

No Known Activations