INDEX

Explanations

elements of a message that indicate editing or updates

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 regional

-0.51

akova

-0.47

 равно

-0.44

 equal

-0.44

ứng

-0.44

fert

-0.42

 phép

-0.41

nof

-0.41

 local

-0.40

门

-0.38

POSITIVE LOGITS

TagMode

1.10

principalColumn

1.03

BeginContext

0.99

 surla

0.86

\{\\

0.83

AnchorStyles

0.83

 ویکی‌پدیا

0.82

migrationBuilder

0.80

ReusableCell

0.79

StoryboardSegue

0.79

Activations Density 0.182%

elements of a message that indicate editing or updates

No Comments

No Known Activations