INDEX

Explanations

metadata related to document processing and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

UIControlState

-0.73

 дописавши

-0.71

MigrationBuilder

-0.60

 Bioaccumulative

-0.60

 kaynağından

-0.57

شهاد

-0.56

ectoria

-0.56

AddTagHelper

-0.56

KURZBESCHREIBUNG

-0.55

andReturn

-0.54

POSITIVE LOGITS

readFileSync

0.58

Hentet

0.57

decode

0.56

 Komunikasi

0.54

 Bretaña

0.53

 Pode

0.53

FunctionFlags

0.52

bersicht

0.51

NAN

0.51

 Comprometido

0.51

Activations Density 0.217%

metadata related to document processing and updates

No Comments

No Known Activations