INDEX

Explanations

phrases related to changes in state or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setInt

-0.60

tuy

-0.57

ADT

-0.56

JR

-0.56

nameof

-0.55

ADT

-0.54

المشاركات

-0.54

ofos

-0.53

atoire

-0.52

didSet

-0.52

POSITIVE LOGITS

 Wikispecies

0.67

InputBorder

0.67

AnchorStyles

0.65

 meurt

0.65

 dries

0.60

 Normdatei

0.59

Clik

0.58

inigte

0.58

 internetowa

0.57

CrossRef

0.57

Activations Density 0.517%

phrases related to changes in state or conditions

No Comments

No Known Activations