INDEX

Explanations

code constructs related to variable declarations and function definitions

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

mixed languages, code, archaic characters

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

 ***!

-0.47

@"/

-0.47

InteropServices

-0.45

istoitu

-0.44

__;

-0.44

__(/*!

-0.44

انجليز

-0.43

تقاوى

-0.43

enumii

-0.43

 Signalez

-0.42

POSITIVE LOGITS

########.

0.51

يكب

0.45

KommentareTeilen

0.42

 vård

0.42

appui

0.41

Slf

0.41

Eſ

0.41

 Houſe

0.41

 eslint

0.41

ſs

0.40

Activations Density 0.078%

code constructs related to variable declarations and function definitions

mixed languages, code, archaic characters

No Comments

No Known Activations