INDEX

Explanations

key terms and phrases related to assessment or evaluation of conditions or attributes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dAtA

-0.47

tières

-0.45

netbeans

-0.44

клопе

-0.43

Inc

-0.42

XLSX

-0.42

极为

-0.42

slidesToShow

-0.41

íná

-0.41

 Geld

-0.41

POSITIVE LOGITS

abestanden

0.79

ScopeManager

0.78

Geplaatst

0.76

 StringTokenizer

0.76

rungsseite

0.71

+#+#

0.71

 تضيفلها

0.70

awtextra

0.69

 مشين

0.67

 CreateTagHelper

0.64

Activations Density 0.492%

key terms and phrases related to assessment or evaluation of conditions or attributes

No Comments

No Known Activations