INDEX

Explanations

commentary or notation in programming or technical documentation

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

mathematical expressions

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

+#+#

-0.59

uxxxx

-0.56

LLocation

-0.53

 Administrativna

-0.52

aarrggbb

-0.52

 betweenstory

-0.52

oredCriteria

-0.51

EDEFAULT

-0.50

 HttpNotFound

-0.50

يكب

-0.48

POSITIVE LOGITS

 vœux

0.40

 Offisielt

0.35

 reaſon

0.35

 ſhe

0.34

migrationBuilder

0.34

ⓧ

0.33

Pemer

0.33

 pères

0.33

 ſtate

0.32

下载附件

0.32

Activations Density 0.000%

commentary or notation in programming or technical documentation

mathematical expressions

No Comments

No Known Activations