INDEX

Explanations

references to military service and history, particularly in relation to World Wars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 initComponents

-0.54

makeConstraints

-0.52

 createState

-0.50

RenderAtEndOf

-0.48

Референце

-0.48

loco

-0.46

 Bhattach

-0.46

Gossip

-0.46

arakat

-0.45

 handleSubmit

-0.45

POSITIVE LOGITS

 militaires

0.56

 soldier

0.52

 military

0.52

 Military

0.50

 militaire

0.47

Military

0.47

military

0.46

 soldiers

0.43

Soldier

0.43

Soldiers

0.42

Activations Density 0.012%

references to military service and history, particularly in relation to World Wars

No Comments

No Known Activations