INDEX

Explanations

technical terms and concepts related to programming and statistical analysis

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

QMetaType

-0.59

Gav

-0.54

 τί

-0.53

 Kien

-0.52

 zewnętrzne

-0.51

iores

-0.50

 financeira

-0.49

pitre

-0.49

帖最后由

-0.49

 postIndex

-0.49

POSITIVE LOGITS

 caufe

0.68

 themſelves

0.67

 Diſ

0.65

 Barbour

0.64

 cauſe

0.61

DoubleQuotes

0.60

__*/

0.58

 pertin

0.58

FK

0.57

Jeb

0.57

Activations Density 2.621%

technical terms and concepts related to programming and statistical analysis

No Comments

No Known Activations