INDEX

Explanations

numeric values and symbols typically used in codes or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

MigrationBuilder

-0.85

 disambiguazione

-0.74

Filmographie

-0.66

 CURIAM

-0.64

djangoproject

-0.63

saraba

-0.62

:+:

-0.62

دانشنامهٔ

-0.61

Obrázky

-0.61

 paramString

-0.61

POSITIVE LOGITS

 esternos

0.52

че

0.46

InSection

0.45

 immune

0.44

enity

0.44

 Immune

0.44

بسم

0.42

 précé

0.41

MP

0.40

 विश्वसनीयता

0.39

Activations Density 0.508%

numeric values and symbols typically used in codes or mathematical expressions

No Comments

No Known Activations