INDEX

Explanations

terms and phrases related to legal or formal documentation

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

?>>

-0.51

addPreferredGap

-0.48

Hil

-0.43

boolean

-0.43

De

-0.43

Di

-0.43

Do

-0.42

torre

-0.42

hop

-0.42

RegressionTest

-0.41

POSITIVE LOGITS

sizeCache

0.75

mybatisplus

0.74

PhysRevD

0.74

WebMethod

0.74

XmlAccessType

0.74

actionMode

0.70

 doInBackground

0.66

Eksterne

0.65

 actionMode

0.64

NameInMap

0.63

Activations Density 0.782%

terms and phrases related to legal or formal documentation

No Comments

No Known Activations