INDEX

Explanations

specific names of places, individuals, and medical conditions

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

 Mant

-0.72

قامة

-0.67

 Sole

-0.66

UGC

-0.66

NUMX

-0.66

Cama

-0.65

 barracks

-0.65

ức

-0.64

Hos

-0.64

étés

-0.62

POSITIVE LOGITS

 ModelExpression

0.77

Посилання

0.74

 verwijzen

0.70

 فريبيس

0.68

 Nadel

0.68

 referenties

0.67

 panela

0.67

 BehaviorSubject

0.67

oa̍t

0.67

FieldDescriptor

0.67

Activations Density 1.554%

specific names of places, individuals, and medical conditions

No Comments

No Known Activations