INDEX

Explanations

references to historical empires and political entities

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

historical empires and states

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelben

-0.63

 оригіналу

-0.61

⤞

-0.60

wiliwch

-0.60

 betweenstory

-0.59

RenderAtEndOf

-0.58

 queſta

-0.56

+#+

-0.56

ſſung

-0.56

#+#

-0.55

POSITIVE LOGITS

 käs

0.31

paraíso

0.30

 uitzicht

0.30

 aikana

0.30

ChildIndex

0.30

 ennen

0.29

 tutkim

0.29

 Dritten

0.29

LookAnd

0.28

 levens

0.28

Activations Density 0.049%

references to historical empires and political entities

historical empires and states

No Comments

No Known Activations