INDEX

Explanations

specific terms and elements related to mathematical models and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

mö

-0.54

кар

-0.53

 otomatig

-0.52

chos

-0.52

 Gans

-0.50

']=='

-0.49

DYNAMIC

-0.49

печат

-0.48

ised

-0.48

ią

-0.48

POSITIVE LOGITS

+#+#

1.04

URLException

1.04

ⓧ

0.97

StoryboardSegue

0.92

extAlignment

0.92

 Autorizaciones

0.87

ruptedException

0.86

ArgsConstructor

0.86

 AssemblyVersion

0.86

ImageContext

0.85

Activations Density 0.571%

specific terms and elements related to mathematical models and notations

No Comments

No Known Activations