INDEX

Explanations

terms related to standalone functionality and independence

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

standalone, alone, own, itself

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

 Erwachsene

-0.26

↵

-0.26

 yakın

-0.25

 yoktur

-0.24

 óptica

-0.24

 místo

-0.23

 dieselben

-0.23

 scène

-0.23

 soon

-0.23

 posiciones

-0.23

POSITIVE LOGITS

 standalone

0.88

standalone

0.82

 Itself

0.80

Standalone

0.76

itself

0.76

 itſelf

0.74

BorderFactory

0.71

 самостоя

0.71

alone

0.70

 itself

0.70

Activations Density 0.042%

terms related to standalone functionality and independence

standalone, alone, own, itself

No Comments

No Known Activations