INDEX

Explanations

assertions about the properties or behaviors of particles and their interactions

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

Follows the word "is" or "are"

np_acts-logits-general · gemini-2.0-flash

is/are followed by state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

BufferException

-0.30

താ

-0.29

Последние

-0.27

 tels

-0.26

 acest

-0.26

InstrumentedTest

-0.25

municipi

-0.25

 contando

-0.25

xrLabel

-0.24

 letting

-0.24

POSITIVE LOGITS

RTDA

0.75

 capable

0.69

 characterized

0.68

 believed

0.67

 characterised

0.65

 generally

0.65

 highly

0.64

 zoude

0.63

 unable

0.62

 weakly

0.62

Activations Density 1.486%

assertions about the properties or behaviors of particles and their interactions

Follows the word "is" or "are"

is/are followed by state

No Comments

No Known Activations