INDEX

Explanations

phrases related to legal or licensing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

WriteLiteral

-0.54

ériques

-0.54

достатки

-0.52

ButterKnife

-0.52

heimer

-0.52

nonumber

-0.48

cellaneous

-0.48

TextAppearance

-0.47

 שוליים

-0.47

phazard

-0.47

POSITIVE LOGITS

 TextInputType

0.75

 autorytatywna

0.70

bewerken

0.65

Personendaten

0.63

 betweenstory

0.58

 Duckworth

0.58

 beginnetje

0.56

saraba

0.55

پیوند

0.53

Tbh

0.52

Activations Density 0.015%

phrases related to legal or licensing information

No Comments

No Known Activations