INDEX

Explanations

technical terms and components related to software development and programming frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AnchorStyles

-0.79

TagHelper

-0.78

ViewImports

-0.77

tagHelperRunner

-0.75

SourceChecksum

-0.73

mergeFrom

-0.71

ruptcy

-0.68

 navideña

-0.67

MessageTagHelper

-0.67

RegressionTest

-0.66

POSITIVE LOGITS

 itself

0.73

 version

0.65

®

0.58

 instance

0.58

based

0.57

 users

0.56

itself

0.56

 core

0.56

上で

0.54

Activations Density 0.555%

technical terms and components related to software development and programming frameworks

No Comments

No Known Activations