INDEX

Explanations

numerical values related to product specifications or system features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

bitField

-0.53

lusconi

-0.47

Portale

-0.47

 &___

-0.47

glVertex

-0.47

argli

-0.46

calciatore

-0.44

 iVar

-0.44

RegressionTest

-0.44

 Mara

-0.44

POSITIVE LOGITS

 enfans

0.49

 propOrder

0.42

 incomplète

0.41

addPreferredGap

0.41

awtextra

0.41

 AsyncTask

0.41

 InputDecoration

0.40

 MainAxisSize

0.40

Vanjske

0.40

 externi

0.40

Activations Density 0.788%

numerical values related to product specifications or system features

No Comments

No Known Activations