INDEX

Explanations

references to specific technical processes and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

willReturn

-0.48

 bulunabilir

-0.44

 breve

-0.44

SizeF

-0.43

ョ

-0.42

 CURLOPT

-0.42

InteropServices

-0.42

tól

-0.42

нш

-0.42

 razones

-0.41

POSITIVE LOGITS

 "..\..\

0.83

__*/

0.80

afficheront

0.78

 виправивши

0.75

 chi̍t

0.74

 Roskov

0.74

devamını

0.74

hidupan

0.73

 ExecuteAsync

0.73

 vacated

0.70

Activations Density 0.414%

references to specific technical processes and descriptions

No Comments

No Known Activations