INDEX

Explanations

sequences of letters and symbols indicating coding or variable structures

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

Single-letter tokens

np_acts-logits-general · gemini-2.0-flash

mathematical expressions with variables

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

LabelTagHelper

-0.55

 initComponents

-0.53

 kasarigan

-0.53

WebpackPlugin

-0.51

 surla

-0.51

 مشين

-0.50

 Reborn

-0.49

QtWidgets

-0.47

 GenerationType

-0.47

dsk

-0.47

POSITIVE LOGITS

anskje

0.40

SourceChecksum

0.40

Lähteet

0.39

corazón

0.39

 votación

0.38

Información

0.38

 contribución

0.37

 inspección

0.36

Initializable

0.35

 actualidad

0.35

Activations Density 2.023%

sequences of letters and symbols indicating coding or variable structures

Single-letter tokens

mathematical expressions with variables

No Comments

No Known Activations