INDEX

Explanations

terms related to program termination or exit commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

bewerken

-0.90

MigrationBuilder

-0.88

NDR

-0.88

髦

-0.88

endphp

-0.86

Хьажоргаш

-0.84

*/].

-0.82

 Warburton

-0.80

ódio

-0.79

er

-0.78

POSITIVE LOGITS

EXIT

1.25

 EXIT

1.22

 Exit

1.14

Exit

1.09

 exit

1.02

exit

1.00

 exits

0.99

 Quit

0.86

 quit

0.82

exits

0.81

Activations Density 0.075%

terms related to program termination or exit commands

No Comments

No Known Activations