INDEX

Explanations

specific quantifiers and ordinal numbers related to rankings or statistics

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

-0.56

 paling

-0.54

more

-0.53

 besonders

-0.52

-0.51

MORE

-0.51

More

-0.50

POSITIVE LOGITS

=$?

1.29

 StatefulWidget

1.23

NUMX

1.21

 ujednoznacz

1.16

rungsseite

1.11

expandindo

1.06

 StatelessWidget

1.04

 utafitiHapana

1.02

.";

1.02

]){

1.02

Activations Density 0.180%

specific quantifiers and ordinal numbers related to rankings or statistics

No Comments

No Known Activations