INDEX

Explanations

phrases indicating placement or positioning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "place" and its variations 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

externalActionCode

-0.81

esp

-0.68

zzy

-0.63

Suk

-0.62

bie

-0.61

uary

-0.61

rd

-0.60

issance

-0.60

ucci

-0.60

 Lust

-0.58

POSITIVE LOGITS

holders

0.99

holder

0.97

ngth

0.91

 undue

0.87

bos

0.86

sembly

0.85

arnaev

0.83

otom

0.78

 bets

0.78

 restraints

0.77

Activations Density 0.034%

phrases indicating placement or positioning

instances of the word "place" and its variations in various contexts

No Comments

No Known Activations