INDEX

Explanations

sections of code related to error handling or resource management

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

Code or XML elements

np_acts-logits-general · gemini-2.0-flash

github repository urls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 cursos

-0.42

theoremstyle

-0.42

جوايز

-0.42

 wall

-0.41

 سكانية

-0.41

wall

-0.41

evaluator

-0.41

آموزش

-0.40

Civ

-0.40

solver

-0.39

POSITIVE LOGITS

IntoConstraints

0.89

 مرئيه

0.85

bolista

0.70

MENAFN

0.69

+#+#

0.67

yarnpkg

0.65

 ब्रेकडाउन

0.64

expandindo

0.63

TypedDataSet

0.60

BeginContext

0.60

Activations Density 0.188%

sections of code related to error handling or resource management

Code or XML elements

github repository urls

No Comments

No Known Activations