INDEX

Explanations

programming terms and code structures related to assemblies and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

expandindo

-0.67

 betweenstory

-0.66

RegressionTest

-0.65

 StringTokenizer

-0.63

 šķ

-0.63

 propOrder

-0.61

EDEFAULT

-0.61

endous

-0.60

 Вікі

-0.60

 nahilalakip

-0.59

POSITIVE LOGITS

쨌

0.59

elle

0.56

 surrender

0.54

fgets

0.53

Roe

0.52

 arşivlendi

0.52

 itinéraires

0.52

widget

0.52

0.50

EnableWeb

0.50

Activations Density 2.577%

programming terms and code structures related to assemblies and data handling

No Comments

No Known Activations