INDEX

Explanations

indicators of structured formatting or references within technical or mathematical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

TagMode

-0.83

 compréhen

-0.64

testens

-0.62

 provisoire

-0.62

_$

-0.61

 AssemblyTitle

-0.60

 reciclaje

-0.58

 виправивши

-0.58

 ainfi

-0.57

 WebDriverWait

-0.57

POSITIVE LOGITS

 تضيفلها

0.67

таратура

0.64

 يتيمه

0.60

 חיצוניים

0.59

 GenerationType

0.57

}{*}{}

0.57

tvguidetime

0.56

enumi

0.56

nonumber

0.56

日閲覧

0.55

Activations Density 0.068%

indicators of structured formatting or references within technical or mathematical documents

No Comments

No Known Activations