INDEX

Explanations

entities and attributes related to data and structures in a systematic manner

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

measurements or proportions

np_acts-logits-general · gemini-2.0-flash

sizes, number, proportion, methodology

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

DrawerToggle

-0.56

AutoScaleMode

-0.54

endphp

-0.51

PreferredItem

-0.49

GraphicsUnit

-0.47

CloseOperation

-0.47

ніципалі

-0.46

makeConstraints

-0.45

 initComponents

-0.44

hyrchwyd

-0.44

POSITIVE LOGITS

 causes

0.43

 remp

0.40

exec

0.39

causes

0.37

fore

0.36

坦

0.35

IVEREF

0.35

emlrt

0.35

KommentareTeilen

0.35

ographers

0.34

Activations Density 1.913%

entities and attributes related to data and structures in a systematic manner

measurements or proportions

sizes, number, proportion, methodology

No Comments

No Known Activations