INDEX

Explanations

numeric data and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

thenReturn

-0.48

庁

-0.48

ashvili

-0.47

вли

-0.46

žuje

-0.45

 Jahrhunderts

-0.45

 certainly

-0.45

```

-0.43

men

-0.43

 estimés

-0.42

POSITIVE LOGITS

 Normdatei

0.77

 moduli

0.65

 Spinoza

0.64

irtschaft

0.64

AnchorStyles

0.64

 >=",

0.63

Efq

0.63

queryInterface

0.62

 Molière

0.62

TypedDataSet

0.60

Activations Density 0.505%

numeric data and measurements

No Comments

No Known Activations