INDEX

Explanations

parentheses and related symbols in mathematical or technical contexts

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

parenthesized words and phrases

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

 panoramique

-0.48

 colgantes

-0.46

 llorando

-0.46

 rojos

-0.46

 magnétique

-0.45

Manbalar

-0.44

 gantung

-0.44

 banderas

-0.44

 cuantos

-0.44

 blancas

-0.44

POSITIVE LOGITS

RTGC

0.64

NameInMap

0.57

Datuak

0.56

 EconPapers

0.54

mybatisplus

0.53

(!)

0.52

(?)

0.51

 linings

0.51

<_>

0.51

(?)

0.49

Activations Density 0.033%

parentheses and related symbols in mathematical or technical contexts

parenthesized words and phrases

No Comments

No Known Activations