INDEX

Explanations

references to scientific publications or research frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

XMLSchema

-0.59

queryInterface

-0.58

posedge

-0.57

ThroughAttribute

-0.57

archiviato

-0.56

/**

-0.55

 Geraadpleegd

-0.55

 Профиль

-0.55

kháu

-0.54

setAccessible

-0.54

POSITIVE LOGITS

 صوتيه

0.50

 يتيمه

0.47

 guides

0.47

 guide

0.46

LookAnd

0.43

objs

0.43

 Wulf

0.41

 object

0.41

int

0.41

fizierung

0.41

Activations Density 1.331%

references to scientific publications or research frameworks

No Comments

No Known Activations