INDEX

Explanations

elements related to user input and calculations in a programming context

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

TF, letter, date, fill, POS

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

 ciasc

-0.45

 ſte

-0.44

 artesanales

-0.44

 particularly

-0.41

anair

-0.40

 hujan

-0.40

 insbesondere

-0.40

 ApiClient

-0.39

 oznacza

-0.39

twimg

-0.39

POSITIVE LOGITS

TagMode

0.65

 يتيمه

0.58

AndEndTag

0.56

 للاسماء

0.49

nezeu

0.49

دانشنامهٔ

0.47

تقاوى

0.45

 незавершена

0.44

cetto

0.44

 فريبيس

0.44

Activations Density 0.025%

elements related to user input and calculations in a programming context

TF, letter, date, fill, POS

No Comments

No Known Activations