INDEX

Explanations

phrases that express uncertainty or doubt

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

Apostrophes followed by specific letters

np_acts-logits-general · gemini-2.0-flash

technical terms and names

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Audiodateien

-0.67

 BoxFit

-0.62

клопе

-0.61

 ivelany

-0.58

PerformLayout

-0.58

 שוליים

-0.57

AddTagHelper

-0.57

</tfoot>

-0.57

存于互联网档案馆

-0.56

 Waray

-0.56

POSITIVE LOGITS

DJANGO

0.58

 ISNI

0.49

 dotenv

0.47

lujah

0.47

nery

0.46

0.45

må

0.45

 действи

0.45

She

0.44

enschaft

0.44

Activations Density 0.077%

phrases that express uncertainty or doubt

Apostrophes followed by specific letters

technical terms and names

No Comments

No Known Activations