INDEX

Explanations

code comments in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 للمعارف

-0.71

 ब्रेकडाउन

-0.63

RegressionTest

-0.62

دانشنامهٔ

-0.62

Autoritní

-0.62

StoryboardSegue

-0.61

GOTREF

-0.60

parsedMessage

-0.58

хьтан

-0.55

 صوتيه

-0.54

POSITIVE LOGITS

 Universitäts

0.41

binaan

0.36

 yapı

0.34

ulihan

0.34

 Cabral

0.33

belajaran

0.33

 présidentielle

0.33

ambilan

0.33

 Rücken

0.32

 oeil

0.32

Activations Density 0.339%

code comments in the document

No Comments

No Known Activations