INDEX

Explanations

phrases related to scientific measurements and results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 social

-0.56

oltán

-0.48

sho

-0.48

</i>

-0.47

 appris

-0.46

 moves

-0.46

fdc

-0.46

 domestic

-0.46

 household

-0.45

“

-0.45

POSITIVE LOGITS

 propOrder

0.99

RenderAtEndOf

0.98

TestBed

0.92

 متعلقه

0.90

 jsPsych

0.84

 initComponents

0.82

 المعيارى

0.81

 auffi

0.80

 تانيه

0.80

__":

0.79

Activations Density 1.605%

phrases related to scientific measurements and results

No Comments

No Known Activations