INDEX

Explanations

references to specific software tools and frameworks

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

Tir

-0.53

mat

-0.53

fio

-0.53

الی

-0.52

ﬄ

-0.52

 Drawn

-0.52

siv

-0.51

istra

-0.50

waw

-0.48

POSITIVE LOGITS

FieldBuilder

0.83

ScopeManager

0.77

قایناقلار

0.75

Zeneca

0.75

 neceff

0.73

 espirituales

0.72

matchCondition

0.72

 &___

0.72

XmlRootElement

0.72

XmlType

0.71

Activations Density 0.025%

references to specific software tools and frameworks

No Comments

No Known Activations