INDEX

Explanations

phrases related to brands, products, and ownership

oai_token-act-pair · gpt-3.5-turbo

elements related to television shows and their production details

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

azeera

-0.77

arent

-0.70

 sidx

-0.62

ynes

-0.56

ernels

-0.51

 spoilers

-0.51

aeda

-0.50

 rebell

-0.49

instein

-0.49

 allies

-0.48

POSITIVE LOGITS

iHUD

0.63

 akin

0.55

 featuring

0.51

Ranked

0.51

sets

0.51

gmail

0.50

Joined

0.49

 accompanies

0.49

 Fresno

0.47

 alongside

0.47

Activations Density 1.824%

phrases related to brands, products, and ownership

elements related to television shows and their production details

No Comments

No Known Activations