INDEX

Explanations

terms related to physical contact or impact

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

bump and impact

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

Activités

-0.33

readAll

-0.31

 Thiel

-0.30

 faccia

-0.29

geb

-0.28

Risultati

-0.28

stdafx

-0.28

ExecuteReader

-0.28

leiter

-0.27

ģ

-0.27

POSITIVE LOGITS

 bumped

1.44

 bumping

1.39

 bump

1.32

 Bump

1.30

bump

1.20

 bumps

1.18

Bump

1.16

BUMP

1.02

bumper

0.93

bumps

0.90

Activations Density 0.007%

terms related to physical contact or impact

bump and impact

No Comments

No Known Activations