INDEX

Explanations

elements related to lines, frames, and instructions in a structured system

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

 AssemblyProduct

-0.62

enez

-0.54

oppa

-0.53

 BoxDecoration

-0.53

шу

-0.52

ERG

-0.52

IEWS

-0.52

insky

-0.52

://"

-0.52

pean

-0.52

POSITIVE LOGITS

Портали

0.66

mybatisplus

0.58

windowFixed

0.58

stander

0.57

ValueStyle

0.57

 Avez

0.57

 Contactez

0.56

Contribute

0.55

ArrowToggle

0.54

 inmobili

0.53

Activations Density 0.848%

elements related to lines, frames, and instructions in a structured system

No Comments

No Known Activations