INDEX

Explanations

terms related to manufacturing and historical records

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

after specific symbols (^, >, <, *) or "established"

np_acts-logits-general · gemini-2.0-flash

established in or completed by

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

?>/

-0.64

发表于

-0.56

GOTREF

-0.49

AddAttribute

-0.49

 Laird

-0.48

väg

-0.46

 {}));

-0.46

 porté

-0.46

GeoNames

-0.46

()]

-0.45

POSITIVE LOGITS

wapV

0.61

ValueGeneration

0.61

 GlobalKey

0.58

 pinulongan

0.58

دانشنامهٔ

0.57

antaine

0.57

НИК

0.56

abestanden

0.55

spora

0.55

 allAfrica

0.54

Activations Density 0.510%

terms related to manufacturing and historical records

after specific symbols (^, >, <, *) or "established"

established in or completed by

No Comments

No Known Activations