INDEX

Explanations

content related to technical specifications and requirements, particularly around definitions and constraints in programming or formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ISupport

-0.87

FormTagHelper

-0.58

__*/

-0.58

RenderAtEndOf

-0.57

@"/

-0.55

 >=",

-0.55

contentLoaded

-0.54

fone

-0.51

GLE

-0.51

($__

-0.50

POSITIVE LOGITS

 belieb

0.61

 dowol

0.58

Cual

0.53

—

0.52

 arbitrary

0.52

INCREF

0.52

škas

0.51

EMON

0.51

構

0.50

 deltag

0.50

Activations Density 0.449%

content related to technical specifications and requirements, particularly around definitions and constraints in programming or formal contexts

No Comments

No Known Activations