INDEX

Explanations

place names and geographic features

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ImageContext

-0.94

 صوتيه

-0.79

">//

-0.79

 ExecuteAsync

-0.78

BeginInit

-0.78

 مشين

-0.76

دانشنامهٔ

-0.74

+#+#

-0.72

 AspNetCore

-0.71

 utafitiHapana

-0.70

POSITIVE LOGITS

 Schne

0.47

 Hager

0.46

TryGetValue

0.46

 artikkelen

0.45

 افت

0.44

 становника

0.44

iecie

0.43

awaiter

0.43

 Inter

0.42

Activations Density 0.537%

place names and geographic features

No Comments

No Known Activations