INDEX

Explanations

terms related to programming and technical functions or methods

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

 grade

-0.50

 тран

-0.48

’

-0.48

<%@

-0.45

-0.44

 against

-0.44

dyr

-0.44

ecutive

-0.42

 которым

-0.42

did

-0.41

POSITIVE LOGITS

Autoritní

1.02

 ISNI

0.82

 HasFactory

0.81

AndroidJUnit

0.74

مراجع

0.73

ⓧ

0.73

 Riproduzione

0.69

 okuyayım

0.68

]")]

0.68

wahati

0.67

Activations Density 0.467%

terms related to programming and technical functions or methods

No Comments

No Known Activations