INDEX

Explanations

classifications and rankings related to medical conditions or roles

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

Classifications or levels, often with Roman numerals

np_acts-logits-general · gemini-2.0-flash

class and stage designations

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

nyv

-0.39

haped

-0.39

 total

-0.39

total

-0.38

 susi

-0.38

Mal

-0.37

 unique

-0.37

Total

-0.37

Unique

-0.36

ружи

-0.36

POSITIVE LOGITS

 level

1.24

 Level

1.18

 LEVEL

1.08

Level

1.07

level

1.06

 Stufe

1.04

 grade

1.01

 nível

1.01

 nivå

1.00

 levels

0.98

Activations Density 0.638%

classifications and rankings related to medical conditions or roles

Classifications or levels, often with Roman numerals

class and stage designations

No Comments

No Known Activations