INDEX

Explanations

proper nouns, specifically names of people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 betweenstory

-0.87

✨:

-0.82

 виправивши

-0.81

rrggbb

-0.80

 continúas

-0.78

 vulgaires

-0.76

 pédagogique

-0.76

 ddelweddau

-0.76

 chrétiens

-0.73

utuhkan

-0.73

POSITIVE LOGITS

ंदीखरीदारी

0.61

 Gewer

0.56

land

0.55

HAB

0.55

כת

0.52

Land

0.52

 Land

0.52

MeasureSpec

0.52

jas

0.51

تها

0.51

Activations Density 0.581%

proper nouns, specifically names of people and organizations

No Comments

No Known Activations