INDEX

Explanations

words related to digital activities and commands

oai_token-act-pair · gpt-3.5-turbo

the end of a document or text segments

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

 Seym

-0.80

emale

-0.75

 destro

-0.75

 Azerb

-0.74

 Frie

-0.73

 disadvant

-0.71

anamo

-0.70

 Vaugh

-0.70

 Niet

-0.70

 submar

-0.69

POSITIVE LOGITS

0.69

able

0.68

 html

0.67

 âĢº

0.65

 guiActiveUnfocused

0.65

ings

0.64

yon

0.63

ables

0.63

ERS

0.62

ths

0.62

Activations Density 0.103%

words related to digital activities and commands

the end of a document or text segments

No Comments

No Known Activations