INDEX

Explanations

terms related to combat or fighting actions

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

enumii

-0.63

 Nikon

-0.52

Raw

-0.51

 Roskov

-0.51

jface

-0.50

scriptcase

-0.50

Pyx

-0.50

庁

-0.48

prepare

-0.48

RAW

-0.47

POSITIVE LOGITS

DeleteBehavior

0.64

 EconPapers

0.60

 Wheeler

0.58

AEW

0.57

ROH

0.57

 Luch

0.57

Wheeler

0.54

GIVEREF

0.54

 cherchés

0.53

 chi̍t

0.53

Activations Density 0.178%

terms related to combat or fighting actions

No Comments

No Known Activations