INDEX

Explanations

references to political roles and positions held by individuals

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

ValueStyle

-0.89

 مشين

-0.87

LookAnd

-0.87

 lenker

-0.84

 AssemblyCulture

-0.79

 governors

-0.78

ImageContext

-0.78

 pinulongan

-0.74

 &___

-0.73

verwijspagina

-0.73

POSITIVE LOGITS

MP

0.54

 circons

0.51

marginVertical

0.49

 StringField

0.46

 constituency

0.45

 seat

0.43

MP

0.42

Shadow

0.42

kozás

0.42

Bronnen

0.41

Activations Density 0.114%

references to political roles and positions held by individuals

No Comments

No Known Activations