INDEX

Explanations

distinctive formatting or markers in the text, particularly tags and special symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.69

EnableWeb

-0.66

enterOuterAlt

-0.56

WebElementEntity

-0.56

webElement

-0.56

SuppressMessage

-0.56

 kasarigan

-0.52

OpenHelper

-0.52

PostInfinity

-0.50

üf

-0.50

POSITIVE LOGITS

 pitié

0.64

 hiér

0.61

 religieuses

0.61

Geplaatst

0.60

 refroid

0.60

MLLoader

0.59

 complètes

0.59

 démission

0.56

 privilégi

0.56

 commerciaux

0.56

Activations Density 0.370%

distinctive formatting or markers in the text, particularly tags and special symbols

No Comments

No Known Activations