INDEX

Explanations

references to political or social entities and geographic locations

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

ValueStyle

-1.00

extAlignment

-0.99

PreferredItem

-0.88

hyrchwyd

-0.86

 nahilalakip

-0.85

+#+#

-0.85

MigrationBuilder

-0.81

 continúas

-0.80

 समीक्षाओं

-0.79

uxxxx

-0.78

POSITIVE LOGITS

has

0.45

 recently

0.45

erste

0.45

0.43

 urged

0.42

ex

0.42

new

0.40

新たな

0.40

‘

0.40

and

0.39

Activations Density 0.299%

references to political or social entities and geographic locations

No Comments

No Known Activations