INDEX

Explanations

instances of the word "woke" in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "woke" or its variations related to waking up

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

inates

-0.75

regate

-0.70

 Proposition

-0.68

abwe

-0.66

 Metropolitan

-0.63

cer

-0.63

entric

-0.60

berus

-0.59

allo

-0.58

inelli

-0.57

POSITIVE LOGITS

mares

1.24

 awake

1.08

 refreshed

1.03

leep

0.89

 awoke

0.87

up

0.85

up

0.85

 awaken

0.84

 woke

0.83

 waking

0.83

Activations Density 0.035%

instances of the word "woke" in different contexts

instances of the word "woke" or its variations related to waking up

No Comments

No Known Activations