INDEX

Explanations

geographical locations and relevant identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 News

-0.52

=$?

-0.49

 hand

-0.47

travis

-0.47

 *)__

-0.45

χω

-0.43

//</

-0.43

News

-0.43

 news

-0.43

תק

-0.43

POSITIVE LOGITS

IntoConstraints

0.80

StoryboardSegue

0.77

 gyhoeddwyd

0.75

 Wiktionnaire

0.74

LookAnd

0.74

цездатний

0.74

 InputDecoration

0.73

RunAsync

0.73

 समीक्षक

0.71

rungsseite

0.70

Activations Density 0.144%

geographical locations and relevant identifiers

No Comments

No Known Activations