INDEX

Explanations

programming-related terms and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

hikari

-0.40

hod

-0.40

〕

-0.38

kam

-0.38

 starts

-0.38

ddr

-0.38

knapp

-0.38

Eff

-0.37

Nod

-0.37

الث

-0.37

POSITIVE LOGITS

DockStyle

1.06

 ModelExpression

0.89

 AttributeSet

0.78

 surla

0.75

脚注の使い方

0.73

sizeCache

0.72

帖最后由

0.69

 صوتيه

0.68

 Autorizaciones

0.68

 Roskov

0.67

Activations Density 1.778%

programming-related terms and syntax

No Comments

No Known Activations