INDEX

Explanations

specific file metadata and details related to programming or coding contexts

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

letters picked

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

InitVars

-0.76

Efq

-0.68

 termica

-0.67

featureID

-0.67

 murale

-0.66

EndGlobalSection

-0.64

 JAXBElement

-0.61

 Vikipedi

-0.61

ByExample

-0.58

Personendaten

-0.58

POSITIVE LOGITS

pulumi

0.68

crose

0.64

 }}"></

0.60

 Rica

0.59

Sal

0.57

osoever

0.57

RefreshLayout

0.55

 press

0.55

Tur

0.54

DispatchToProps

0.52

Activations Density 1.832%

specific file metadata and details related to programming or coding contexts

letters picked

No Comments

No Known Activations