INDEX

Explanations

references to the structure and functionality of programming constructs in code

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

After specific words

np_acts-logits-general · gemini-2.0-flash

identifiers and values

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

‍♀️

-0.55

 boleto

-0.48

‍♂️

-0.48

不已

-0.43

แหล

-0.42

Achtung

-0.41

ầy

-0.41

 लेकर

-0.40

 unrecogn

-0.40

によっては

-0.39

POSITIVE LOGITS

 ویکی‌پدی

1.24

Personensuche

1.18

hoeddwyd

1.17

tagHelperRunner

1.14

 Roskov

1.13

RegressionTest

1.12

 autorytatywna

1.11

OGND

1.11

AccessorTable

1.07

évaluateur

1.07

Activations Density 0.382%

references to the structure and functionality of programming constructs in code

After specific words

identifiers and values

No Comments

No Known Activations