INDEX

Explanations

specific identifier names and numerical values in a programming context

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

Code or calculations involving numbers and symbols

np_acts-logits-general · gemini-2.0-flash

set AccessibleName

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

 Menſchen

-0.79

 imagui

-0.79

 ſeines

-0.77

 queſto

-0.76

 geweſen

-0.76

 Dieſe

-0.76

#+#

-0.75

 erſten

-0.75

 Weiſe

-0.75

ᦺ

-0.75

POSITIVE LOGITS

0.33

geführt

0.32

Ant

0.32

0.30

0.29

ἔ

0.29

Activations Density 1.488%

specific identifier names and numerical values in a programming context

Code or calculations involving numbers and symbols

set AccessibleName

No Comments

No Known Activations