INDEX

Explanations

mathematical expressions and calculations involving numbers and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Lähteet

-0.68

Personensuche

-0.59

imanapun

-0.59

 فريبيس

-0.58

ष्य

-0.58

tok

-0.58

 Largo

-0.58

lar

-0.55

 conc

-0.54

MDC

-0.54

POSITIVE LOGITS

 Bhatt

0.83

 Bhat

0.73

 novios

0.70

Kyo

0.69

 Gehen

0.68

 Stepan

0.67

NRA

0.67

JPL

0.66

 Exacts

0.66

 Vast

0.66

Activations Density 1.098%

mathematical expressions and calculations involving numbers and operations

No Comments

No Known Activations