INDEX

Explanations

proper nouns, particularly names and 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

-0.37

 nearby

-0.27

 domain

-0.27

єте

-0.27

 comprising

-0.27

 here

-0.26

 stade

-0.26

<eos>

-0.26

 Horizonte

-0.26

subsection

-0.25

POSITIVE LOGITS

RenderAtEndOf

0.94

processable

0.63

DockStyle

0.63

 ſei

0.63

 createState

0.63

 propOrder

0.63

 ſeine

0.62

 ModelExpression

0.62

########.

0.61

 AssemblyCulture

0.61

Activations Density 0.411%

proper nouns, particularly names and places

No Comments

No Known Activations