INDEX

Explanations

phrases related to secondary or derivative aspects of something

oai_token-act-pair · gpt-3.5-turbo

references to categories of products and elections

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

ibaba

-0.95

 reside

-0.64

etsk

-0.62

uyomi

-0.62

 belie

-0.61

Sov

-0.60

 awaits

-0.60

owship

-0.59

abi

-0.59

raped

-0.59

POSITIVE LOGITS

NING

0.69

 Means

0.68

 guiActiveUn

0.65

Liter

0.62

LEY

0.62

loading

0.61

committee

0.61

 virtue

0.61

 Numbers

0.61

umbers

0.60

Activations Density 0.204%

phrases related to secondary or derivative aspects of something

references to categories of products and elections

No Comments

No Known Activations