INDEX

Explanations

technical or programming terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 AssemblyProduct

-0.96

帖最后由

-0.88

queryInterface

-0.86

SourceChecksum

-0.81

 مشين

-0.75

 surla

-0.74

typeorm

-0.74

 تكبرها

-0.73

ValueStyle

-0.70

FunctionFlags

-0.70

POSITIVE LOGITS

 kiến

0.46

schemas

0.44

 adopted

0.43

setOnAction

0.43

 MainAxisSize

0.43

 adoption

0.43

LayoutInflater

0.42

urn

0.41

 Hallmark

0.41

 adopción

0.41

Activations Density 0.358%

technical or programming terms

No Comments

No Known Activations

technical or programming terms

No Comments

No Known Activations