INDEX

Explanations

elements related to processes, measurements, and classifications in scientific or analytical contexts

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

CJK

-0.88

enumi

-0.84

saurus

-0.82

 fathoms

-0.78

出版年

-0.77

 ་་

-0.75

 Parthen

-0.75

Zitat

-0.73

 Euphrates

-0.72

 dreamstime

-0.72

POSITIVE LOGITS

ӳ

0.53

0.50

AntiForgeryToken

0.50

in

0.49

sizeCache

0.48

0.47

 mante

0.47

 Brown

0.44

писи

0.44

InitVars

0.44

Activations Density 2.617%

elements related to processes, measurements, and classifications in scientific or analytical contexts

No Comments

No Known Activations