INDEX

Explanations

references to source materials or citations

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

Personendaten

-0.63

aneta

-0.60

};*/

-0.56

!';

-0.56

ValueStyle

-0.55

StoryboardSegue

-0.53

carat

-0.52

AndPassword

-0.52

ParallelGroup

-0.51

GEBURTSDATUM

-0.51

POSITIVE LOGITS

NKC

0.63

AddTagHelper

0.60

MigrationBuilder

0.56

ref

0.55

ref

0.54

ataires

0.53

 urbain

0.52

NamedQueries

0.51

 ControllerBase

0.51

 StatefulWidget

0.51

Activations Density 0.211%

references to source materials or citations

No Comments

No Known Activations