INDEX

Explanations

phrases related to the actions of optimizing and modifying processes or content

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

German words or code-related terms

np_acts-logits-general · gemini-2.0-flash

German modal verbs, states of being

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArrowToggle

-0.70

Personendaten

-0.66

 ſtate

-0.62

تقاوى

-0.61

ThroughAttribute

-0.59

setViewportView

-0.59

 transfieras

-0.58

تفصیلات

-0.58

ViewImports

-0.58

tagez

-0.57

POSITIVE LOGITS

Tên

0.52

therapeutic

0.50

)['

0.49

 oprot

0.48

databind

0.46

\}=\

0.46

ConstraintSet

0.45

 verf

0.45

postcss

0.44

umsi

0.44

Activations Density 0.011%

phrases related to the actions of optimizing and modifying processes or content

German words or code-related terms

German modal verbs, states of being

No Comments

No Known Activations