INDEX

Explanations

technical terms and concepts related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 treated

-0.50

gestellten

-0.49

 laissé

-0.47

 Treated

-0.45

 Breaking

-0.45

 Umgang

-0.45

faden

-0.44

rike

-0.44

רות

-0.44

 része

-0.44

POSITIVE LOGITS

 Walkover

0.79

 Paglinawan

0.77

 ModelExpression

0.76

دانشنامهٔ

0.72

الحياه

0.71

 TextAlign

0.68

 виправивши

0.67

ApiModelProperty

0.67

kloped

0.67

MigrationBuilder

0.66

Activations Density 2.324%

technical terms and concepts related to programming and data structures

No Comments

No Known Activations