INDEX

Explanations

military-related terms and operations

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

 CreateTagHelper

-0.64

 ModelExpression

-0.53

getSystemService

-0.53

 Réponses

-0.52

 Commencez

-0.51

GYPT

-0.50

getDoctrine

-0.50

accio

-0.49

 Ulster

-0.48

 "'");

-0.47

POSITIVE LOGITS

 Guam

0.88

 Marshall

0.81

 Palau

0.80

 Mariana

0.78

Mic

0.78

 Marian

0.77

ato

0.73

Yap

0.73

 Samoa

0.72

Marian

0.71

Activations Density 0.243%

military-related terms and operations

No Comments

No Known Activations