INDEX

Explanations

comparative phrases indicating amounts, speed, or effectiveness in a study or analysis context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 تضيفلها

-0.67

 Escolar

-0.64

WriteAttribute

-0.62

BeginContext

-0.62

mbg

-0.59

 autorytatywna

-0.58

 correctes

-0.57

MeV

-0.57

WindowConstants

-0.56

 maxn

-0.55

POSITIVE LOGITS

 gấp

0.64

倍

0.60

phazard

0.56

 doubling

0.56

 double

0.55

 doubled

0.55

 doubles

0.50

osity

0.49

 вд

0.48

 twice

0.48

Activations Density 0.938%

comparative phrases indicating amounts, speed, or effectiveness in a study or analysis context

No Comments

No Known Activations