INDEX

Explanations

references to programming concepts, particularly related to APIs and data management

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

import statements

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

expandindo

-0.62

parsedMessage

-0.60

invokeLater

-0.55

StoryboardSegue

-0.53

endcsname

-0.53

AccessorTable

-0.51

Personensuche

-0.51

interopRequire

-0.50

 ArrayAdapter

-0.50

MessageOf

-0.49

POSITIVE LOGITS

RectangleBorder

0.48

 elettrico

0.43

wachsenen

0.43

省市镇

0.42

 compliqué

0.41

 gyhoeddwyd

0.41

 Highlands

0.41

 tertentu

0.40

 titulares

0.40

 Paesi

0.40

Activations Density 0.005%

references to programming concepts, particularly related to APIs and data management

import statements

No Comments

No Known Activations