INDEX

Explanations

information related to patent applications and references

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

patent and application numbers

np_acts-logits-general · gemini-2.0-flash

specific identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

цездатний

-0.68

</thead>

-0.66

astéro

-0.65

^(@)

-0.63

żer

-0.62

 Forumite

-0.60

İY

-0.59

 Exacts

-0.59

請繼續往下閱讀

-0.58

BeginContext

-0.57

POSITIVE LOGITS

FormTagHelper

0.57

aarrggbb

0.54

 issued

0.52

0.50

NewUrlParser

0.49

 fundamentos

0.47

\&

0.47

号

0.45

issued

0.45

KURZBESCHREIBUNG

0.44

Activations Density 1.203%

information related to patent applications and references

patent and application numbers

specific identifiers

No Comments

No Known Activations