INDEX

Explanations

technical updates and changes related to software or programming

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

software versions and releases

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

LEGGI

-0.49

 aikaa

-0.49

ijiet

-0.48

 kirja

-0.48

 julk

-0.46

 Könige

-0.46

 Italij

-0.45

 näytte

-0.42

ſelf

-0.42

 myö

-0.42

POSITIVE LOGITS

 version

0.54

>--}}

0.45

 versions

0.44

OrBuilder

0.44

 fresher

0.43

endsection

0.43

wapV

0.42

version

0.42

 версия

0.41

 preprint

0.41

Activations Density 0.032%

technical updates and changes related to software or programming

software versions and releases

No Comments

No Known Activations