INDEX

Explanations

code-related terminology and structures, particularly those involving object references, data management, and variable initialization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

adaptiveStyles

-0.54

 يتيمه

-0.46

OrWhiteSpace

-0.46

袈

-0.43

عنوان

-0.43

мерть

-0.42

lapsingToolbar

-0.42

ดับ

-0.41

SuspendLayout

-0.41

POSITIVE LOGITS

 retval

0.65

 retVal

0.63

 évaluations

0.62

.")]

0.61

consulté

0.59

 pleaſure

0.59

 Leif

0.58

 Allegretto

0.57

'])

0.56

Etr

0.56

Activations Density 0.113%

code-related terminology and structures, particularly those involving object references, data management, and variable initialization

No Comments

No Known Activations