INDEX

Explanations

instances of the word "let" and its variations, indicating themes of permission and release

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

argout

-0.64

Filmographie

-0.64

érape

-0.62

findpost

-0.57

vimento

-0.56

ukone

-0.54

</table>

-0.52

delwed

-0.51

agramm

-0.51

 Warhol

-0.51

POSITIVE LOGITS

LET

0.83

 lets

0.79

let

0.78

Letting

0.77

 Letting

0.76

principalColumn

0.75

 letting

0.73

tuce

0.70

byg

0.69

GeoNames

0.69

Activations Density 0.135%

instances of the word "let" and its variations, indicating themes of permission and release

No Comments

No Known Activations