INDEX

Explanations

programming constructs and operations related to data handling and error management

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

Code snippets (often Go files)

np_acts-logits-general · gemini-2.0-flash

return cram, username, password, server

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 seem

-0.56

 onPostExecute

-0.54

 today

-0.53

{{/

-0.53

(;;

-0.52

 seems

-0.52

hoy

-0.50

ReusableCell

-0.50

 tonight

-0.49

Al

-0.49

POSITIVE LOGITS

sizeCache

0.83

 Bourgoin

0.69

 ErrIntOverflow

0.69

rawDesc

0.67

 ویکی‌پدی

0.67

Diwedd

0.66

 pleaſure

0.65

ⓧ

0.65

protoimpl

0.65

riwal

0.65

Activations Density 0.820%

programming constructs and operations related to data handling and error management

Code snippets (often Go files)

return cram, username, password, server

No Comments

No Known Activations