INDEX

Explanations

technical terms and components related to software structure and functionality

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

AsUp

-0.88

SuspendLayout

-0.56

addContainerGap

-0.50

resave

-0.50

 TÉCN

-0.49

rekli

-0.47

eadilan

-0.47

WithMany

-0.47

StructEnd

-0.46

bootstrapcdn

-0.46

POSITIVE LOGITS

ExecutionContext

1.64

tagHelperRunner

0.73

 referrerpolicy

0.70

FunctionFlags

0.59

SerializedName

0.58

webElementGuid

0.57

 Expl

0.57

 Marrow

0.56

AddTagHelper

0.56

 Roskov

0.55

Activations Density 0.008%

technical terms and components related to software structure and functionality

No Comments

No Known Activations