INDEX

Explanations

HTML comment tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 ObjectMapper

-0.46

 mascotas

-0.42

 coloriage

-0.42

 escolares

-0.41

 muñecas

-0.40

 MainAxisSize

-0.40

 škole

-0.40

iyaki

-0.39

Gizmos

-0.39

providedIn

-0.39

POSITIVE LOGITS

<!--

1.41

 <!--

1.19

><!--

0.95

"><!--

0.85

<!--

0.77

-->

0.71

<!--<

0.64

<--

0.57

←

0.57

<!--[

0.57

Activations Density 0.149%

HTML comment tags

No Comments

No Known Activations