INDEX

Explanations

references to data structures and objects related to coding and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

moveToFirst

-0.82

 MainAxisSize

-0.76

tvguidetime

-0.75

 Roskov

-0.70

 russes

-0.68

 firebaseConfig

-0.68

 tartalomajánló

-0.66

 दें

-0.63

 ContentValues

-0.63

WebServlet

-0.63

POSITIVE LOGITS

rate

0.87

rated

0.75

rates

0.68

{@

0.67

ten

0.66

 nervous

0.65

 nerve

0.63

 nerv

0.56

Capítulo

0.54

 nerves

0.53

Activations Density 0.059%

references to data structures and objects related to coding and programming

No Comments

No Known Activations