INDEX

Explanations

programming logic and data processing terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 kasarigan

-0.57

RTLR

-0.54

 समीक्षक

-0.50

transQ

-0.49

-------------</

-0.47

Билгалдахарш

-0.47

Autoritní

-0.45

BibitemShut

-0.44

ècie

-0.43

setCellStyle

-0.43

POSITIVE LOGITS

OCCURRED

0.45

StoryboardSegue

0.42

ChromeDriver

0.41

 AssemblyVersion

0.36

ędzy

0.35

 INTERESAR

0.35

 فريبيس

0.34

-(-

0.34

SystemColors

0.33

 difference

0.33

Activations Density 0.483%

programming logic and data processing terminology

No Comments

No Known Activations