INDEX

Explanations

phrases related to destruction or conflict

oai_token-act-pair · gpt-3.5-turbo

the preposition "of" in various contexts

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

ucci

-0.56

 reperto

-0.53

 destro

-0.53

acus

-0.50

wagon

-0.50

 challeng

-0.49

 caut

-0.49

 describ

-0.48

wcs

-0.48

rul

-0.47

POSITIVE LOGITS

 JUSTICE

0.48

 sorts

0.48

 course

0.48

icial

0.42

 Science

0.41

 Gear

0.40

 doom

0.40

 Darkness

0.40

 Investigation

0.40

 RELE

0.40

Activations Density 0.453%

phrases related to destruction or conflict

the preposition "of" in various contexts

No Comments

No Known Activations