INDEX

Explanations

symbols and formatting elements related to code and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

PerPage

-0.47

rix

-0.46

ctibles

-0.45

quel

-0.43

pertory

-0.43

诲

-0.41

}^{*}\

-0.41

)|\

-0.41

SL

-0.41

rzej

-0.41

POSITIVE LOGITS

Personensuche

1.07

ⓧ

0.90

NameInMap

0.84

 nakalista

0.83

InitVars

0.75

ReusableCell

0.74

TestingModule

0.72

enterOuterAlt

0.72

rungsseite

0.72

 nahilalakip

0.72

Activations Density 0.040%

symbols and formatting elements related to code and documentation

No Comments

No Known Activations