INDEX

Explanations

references to specific technical terms and concepts related to analysis and measurements in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.90

HideFlags

-0.84

+#+#

-0.83

 Winaray

-0.74

__':

-0.67

Демографія

-0.65

.*")]

-0.65

 transférez

-0.64

verifyException

-0.64

AutoScaleMode

-0.63

POSITIVE LOGITS

is

0.47

 TextEditing

0.46

 respectively

0.46

and

0.46

etc

0.45

nextProps

0.44

ViewImports

0.44

0.42

 HttpStatusCode

0.42

usermodel

0.42

Activations Density 0.770%

references to specific technical terms and concepts related to analysis and measurements in various contexts

No Comments

No Known Activations