INDEX

Explanations

numerical values or statistical data

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

numbers and symbols

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

Autoritní

-0.63

himovic

-0.54

AndEndTag

-0.51

 ſtand

-0.51

 ArrayAdapter

-0.51

VIAF

-0.50

SceneManagement

-0.49

mybatisplus

-0.49

EndContext

-0.49

ffindor

-0.49

POSITIVE LOGITS



0.45

InputTagHelper

0.41

half

0.38

issue

0.36

 puissiez

0.36

 iprot

0.35

queryInterface

0.35

indest

0.34

mahaman

0.34

رشف

0.34

Activations Density 0.162%

numerical values or statistical data

numbers and symbols

No Comments

No Known Activations