INDEX

Explanations

programming syntax elements and operators

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

structured data keys

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

Negative Logits

 fazenda

-0.51

 dourada

-0.48

 cortinas

-0.47

 pido

-0.45

 Perdana

-0.45

jā

-0.45

 crees

-0.45

kjø

-0.44

verket

-0.44

utuhkan

-0.44

POSITIVE LOGITS

jsonwebtoken

0.56

pvc

0.52

Mio

0.52

 tuba

0.51

ceğine

0.51

 AssemblyCompany

0.51

بوابة

0.51

HandlerContext

0.50

 مرئيه

0.50

abstractmethod

0.50

Activations Density 0.021%

programming syntax elements and operators

structured data keys

No Known Activations