INDEX

Explanations

mathematical or statistical notation and expressions

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

F<sub>ST</sub> statistical term

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

TagMode

-0.68

GEBURTSDATUM

-0.68

UserScript

-0.68

expandindo

-0.64

RectangleBorder

-0.62

<unused28>

-0.61

<unused43>

-0.61

<unused16>

-0.61

RegressionTest

-0.61

[@BOS@]

-0.61

POSITIVE LOGITS

 again

0.49

同じく

0.36

 wiederum

0.36

 appunto

0.36

internalType

0.35

again

0.34

 nuovamente

0.34

又

0.34

 igjen

0.33

Nationalité

0.32

Activations Density 0.288%

mathematical or statistical notation and expressions

F<sub>ST</sub> statistical term

No Comments

No Known Activations