INDEX

Explanations

specific variable names and function definitions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

OGND

-0.64

:+:

-0.63

ValueGeneration

-0.59

Rhestr

-0.59

migrationBuilder

-0.57

endphp

-0.57

zzleHttp

-0.54

styleType

-0.54

hoeddwyd

-0.54

endpush

-0.53

POSITIVE LOGITS

Nationalité

0.40

 aimez

0.39

 Betracht

0.38

ⓧ

0.37

 Komun

0.36

arnya

0.35

 lista

0.35

Транспорт

0.34

jusi

0.34

Odkazy

0.33

Activations Density 0.098%

specific variable names and function definitions in code

No Comments

No Known Activations