INDEX

Explanations

technical terms and parameters related to system configuration

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

Code or statistics mentioning memory reads

np_acts-logits-general · gemini-2.0-flash

memory read operations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

setupUi

-0.62

ScreenState

-0.59

tvguidetime

-0.58

nelse

-0.58

uzi

-0.56

WebElementEntity

-0.56

 nech

-0.55

Aktualisiert

-0.54

 <>",

-0.54

TintMode

-0.54

POSITIVE LOGITS

 read

0.99

 READ

0.89

 reads

0.89

 Reads

0.81

 reading

0.81

 Read

0.78

 write

0.77

read

0.75

Reads

0.73

 baca

0.72

Activations Density 0.650%

technical terms and parameters related to system configuration

Code or statistics mentioning memory reads

memory read operations

No Comments

No Known Activations