INDEX

Explanations

occurrences of numbers or special characters, particularly in a structured or coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

исленность

-0.69

tonode

-0.54

енча

-0.53

 kohdetta

-0.53

WireFormat

-0.53

amps

-0.52

 Chwiliwch

-0.52

 بتاريخ

-0.52

Carriera

-0.50

 незавершена

-0.50

POSITIVE LOGITS

 utafitiHapana

0.67

WebVitals

0.63

 wikipagina

0.62

reportWebVitals

0.57

tagHelperRunner

0.55

SuppressLint

0.54

 Wart

0.53

VersionUID

0.52

 فريبيس

0.50

IntoConstraints

0.50

Activations Density 0.361%

occurrences of numbers or special characters, particularly in a structured or coding context

No Comments

No Known Activations