INDEX

Explanations

capitalized keywords and phrases that indicate general information or significance

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

number sequences

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

AddTagHelper

-0.41

 Flasche

-0.40

">:

-0.40

 bolsillos

-0.40

ToListAsync

-0.40

 JSONException

-0.40

 gratuites

-0.40

mergeFrom

-0.39

 ComVisible

-0.39

 jurado

-0.39

POSITIVE LOGITS

 Concession

0.47

\{\\

0.47

GEBURTSDATUM

0.44

 koş

0.44

0.43

+#+#

0.42

Clik

0.41

findpost

0.40

bibinfo

0.40

 متعلقه

0.40

Activations Density 0.002%

capitalized keywords and phrases that indicate general information or significance

number sequences

No Comments

No Known Activations