INDEX

Explanations

references to Google and its various services and products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 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

 Pardo

-0.65

 MessageBoxIcon

-0.65

Fech

-0.65

InjectAttribute

-0.63

श्च

-0.62

irts

-0.62

makeConstraints

-0.61

TypedArray

-0.61

astricht

-0.61

<%=

-0.60

POSITIVE LOGITS

 Google

1.71

Google

1.55

 GOOGLE

1.49

 google

1.47

google

1.40

GOOGLE

1.32

GoogleMap

1.31

goog

1.30

 googled

1.18

GoogleApiClient

1.16

Activations Density 0.052%

references to Google and its various services and products

No Comments

No Known Activations