INDEX

Explanations

references to free software and licensing conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

webElementXpaths

-0.81

 cherchés

-0.76

elemField

-0.76

 muualla

-0.71

Datuak

-0.70

 חיצוניים

-0.69

 بيها

-0.69

TintMode

-0.68

 виправивши

-0.68

BeginContext

-0.67

POSITIVE LOGITS

HKEY

0.45

 Poincar

0.45

INKS

0.43

NA

0.41

meu

0.41

med

0.41

oquia

0.40

ietf

0.40

ppur

0.40

 iodide

0.40

Activations Density 0.693%

references to free software and licensing conditions

No Comments

No Known Activations