INDEX

Explanations

specific names and references, including proper nouns and identifiers

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

ת

-0.50

ator

-0.49

ian

-0.47

 recorrer

-0.46

les

-0.45

ador

-0.44

子的

-0.42

les

-0.42

ATOR

-0.42

ula

-0.42

POSITIVE LOGITS

 ModelExpression

0.94

 betweenstory

0.78

saraba

0.78

 Administrativna

0.77

VersionUID

0.73

 AssemblyCulture

0.72

GEBURTSDATUM

0.71

 dalamnya

0.70

MigrationBuilder

0.68

 <>",

0.68

Activations Density 0.202%

specific names and references, including proper nouns and identifiers

No Comments

No Known Activations