INDEX

Explanations

sequences or patterns related to numerical data or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

mybatisplus

-0.72

 مرئيه

-0.68

 تكبرها

-0.64

ulite

-0.63

 يتيمه

-0.63

LLocation

-0.58

 publiques

-0.56

 épar

-0.56

المناصب

-0.54

 esternos

-0.54

POSITIVE LOGITS

AndEndTag

0.78

webElement

0.60

isfile

0.58

 AssemblyCompany

0.57

 урна

0.57

abcdef

0.56

CppCodeGen

0.55

nsic

0.55

oursquare

0.53

FormState

0.52

Activations Density 0.682%

sequences or patterns related to numerical data or measurements

No Comments

No Known Activations