INDEX

Explanations

programming syntax and structure

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

Code snippets or parts of code

np_acts-logits-general · gemini-2.0-flash

code execution and output

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 мәкал

-0.54

adaptiveStyles

-0.49

 kasarigan

-0.49

BeginContext

-0.46

 كومونز

-0.44

setArguments

-0.43

Spoljašnje

-0.42

例文帳に追加

-0.42

Rohy

-0.41

 المعيارى

-0.41

POSITIVE LOGITS

ついでに

0.48

phors

0.47

 encima

0.46

sequently

0.45

Vader

0.44

 also

0.44

ntz

0.43

AMT

0.42

 ayrıca

0.42

Télécharger

0.42

Activations Density 1.103%

programming syntax and structure

Code snippets or parts of code

code execution and output

No Comments

No Known Activations