INDEX

Explanations

numeric values or numerical lists

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

 Monark

-0.59

limin

-0.58

leh

-0.55

mpo

-0.55

daan

-0.55

 Halen

-0.55

 abond

-0.55

mun

-0.54

جغرافيا

-0.54

墨

-0.53

POSITIVE LOGITS

ValueStyle

0.81

 оригіналу

0.79

djangoproject

0.77

 ویکی‌پدی

0.74

StoryboardSegue

0.74

 calendriers

0.74

 مشين

0.72

 Geraadpleegd

0.71

HasMaxLength

0.68

hmigung

0.67

Activations Density 0.093%

numeric values or numerical lists

No Comments

No Known Activations