INDEX

Explanations

structural components commonly seen in documentation or coding reference materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 financières

-0.65

ļi

-0.59

umą

-0.58

lewati

-0.58

 commerciales

-0.57

 auguri

-0.57

ENDIAN

-0.56

 dinámico

-0.56

 juridiques

-0.55

 tiennent

-0.55

POSITIVE LOGITS

 ProtoMessage

0.87

 autorytatywna

0.86

subsection

0.73

 createSlice

0.72

省市镇

0.72

 NgModule

0.70

Personensuche

0.66

subsubsection

0.65

ApiProperty

0.64

 AssemblyTitle

0.61

Activations Density 0.137%

structural components commonly seen in documentation or coding reference materials

No Comments

No Known Activations