INDEX

Explanations

scientific terms related to biology and medical research

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

preceding technical terms

np_acts-logits-general · gemini-2.0-flash

specific nouns

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 helft

-0.63

 zijne

-0.58

 Савезне

-0.57

 oorsp

-0.53

 indruk

-0.52

 zilver

-0.49

 мәкал

-0.49

 Helms

-0.47

AxisAlignment

-0.47

 ardından

-0.46

POSITIVE LOGITS

帖最后由

0.43

 cadet

0.42

 متعلقه

0.42

 vito

0.40

cæ

0.40

 Chriftian

0.40

 Garantía

0.39

 ſche

0.39

enderror

0.38

KPI

0.38

Activations Density 1.378%

scientific terms related to biology and medical research

preceding technical terms

specific nouns

No Comments

No Known Activations