INDEX

Explanations

programming keywords and operators in code snippets

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

mathematical symbols and expressions

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

setVerticalGroup

-0.46

Clik

-0.46

 Fortuna

-0.45

الحياه

-0.45

ceğini

-0.44

itettura

-0.44

 reckoned

-0.44

rews

-0.42

quez

-0.42

delwed

-0.42

POSITIVE LOGITS

 мәкал

0.52

MigrationBuilder

0.52

 lección

0.51

 Comprometido

0.50

 civilización

0.49

 󰀄

0.47

pecabe

0.45

 CanadaChoose

0.45

 cív

0.45

 leão

0.45

Activations Density 0.011%

programming keywords and operators in code snippets

mathematical symbols and expressions

No Comments

No Known Activations