INDEX

Explanations

terms related to statistical or mathematical concepts

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

Followed by journal titles or location names

np_acts-logits-general · gemini-2.0-flash

journal titles and references

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

CORBA

-0.50

stateMutability

-0.49

 telev

-0.49

__*/

-0.48

нциклопедия

-0.47

 quedarse

-0.47

 Nanotechnology

-0.47

 salsa

-0.45

 ویکی‌پدیا

-0.45

 للاسماء

-0.45

POSITIVE LOGITS

 Administrativna

0.68

#+#

0.66

 AppCompatTheme

0.66

 Monthly

0.62

ագրություններ

0.62

 reprints

0.60

 specialmente

0.60

ⓧ

0.59

 تضيفلها

0.59

 researches

0.58

Activations Density 0.455%

terms related to statistical or mathematical concepts

Followed by journal titles or location names

journal titles and references

No Comments

No Known Activations