INDEX

Explanations

geographical locations and references to various places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

use

-0.34

ptăm

-0.34

Fig

-0.34

__((

-0.33

dstuk

-0.33

 prin

-0.33

 string

-0.33

pantalla

-0.32

Busqueda

-0.32

unakan

-0.32

POSITIVE LOGITS

 CreateTagHelper

0.73

+#+

0.72

 disambiguazione

0.70

IContainer

0.69

 defaultstate

0.66

脚注の使い方

0.65

 Paglinawan

0.63

:+:

0.62

########.

0.60

 AspNetCore

0.59

Activations Density 0.295%

geographical locations and references to various places

No Comments

No Known Activations