INDEX

Explanations

visual symbols or indicators related to data and measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 AssemblyTitle

-0.61

--){

-0.57

shadowOpacity

-0.54

')){

-0.52

skraft

-0.51

unately

-0.50

")){

-0.49

 tả

-0.49

cabul

-0.48

skab

-0.46

POSITIVE LOGITS

ConstraintMaker

0.83

ValueStyle

0.68

posedge

0.67

IntoConstraints

0.65

 onAnimation

0.63

fromnode

0.61

InvalidProtocol

0.59

 midnight

0.58

PhysRevD

0.58

 CreateTagHelper

0.58

Activations Density 0.194%

visual symbols or indicators related to data and measurement

No Comments

No Known Activations