INDEX

Explanations

proper nouns, particularly names and specific entities related to individuals and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 للمعارف

-0.83

 Schmitz

-0.81

----</

-0.76

 Zapo

-0.75

 perche

-0.75

 olives

-0.75

 Conley

-0.73

見つ

-0.72

 Benitez

-0.71

 Hierro

-0.69

POSITIVE LOGITS

TypedDataSet

0.80

Xna

0.73

 grains

0.69

Abitanti

0.64

 grain

0.64

Tam

0.63

Armenia

0.63

 Korn

0.63

Tam

0.62

 Grains

0.61

Activations Density 2.264%

proper nouns, particularly names and specific entities related to individuals and places

No Comments

No Known Activations