INDEX

Explanations

references to mountains and similar geographic entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

interopRequire

-0.74

новниш

-0.74

躇

-0.69

tanleria

-0.69

 بيها

-0.67

 okuyayım

-0.62

ingale

-0.60

Geplaatst

-0.59

 prés

-0.58

ViewFeatures

-0.58

POSITIVE LOGITS

 Mount

0.93

Mount

0.89

Mt

0.84

 mountain

0.83

 Mountain

0.78

 MOUNT

0.78

 mounts

0.77

Mt

0.77

 Mounts

0.75

Mountain

0.73

Activations Density 0.075%

references to mountains and similar geographic entities

No Comments

No Known Activations