INDEX

Explanations

terms related to normalization and measurement in data analysis processes

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

.*")]

-0.53

 Bier

-0.53

 Holland

-0.49

tagext

-0.49

krieg

-0.48

currentThread

-0.47

dataIndex

-0.47

ISTRO

-0.46

}</

-0.46

ellus

-0.46

POSITIVE LOGITS

MigrationBuilder

0.65

 betweenstory

0.61

 standardize

0.59

 standardized

0.58

SharedCtor

0.57

 الدولى

0.54

 >=",

0.53

jsonwebtoken

0.52

 standardi

0.51

phosa

0.50

Activations Density 0.939%

terms related to normalization and measurement in data analysis processes

No Comments

No Known Activations