INDEX

Explanations

syntax and structure specific to programming or data manipulation within Python, particularly related to DataFrames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Mix

-0.56

BeginContext

-0.53

 campuran

-0.52

 confusion

-0.51

 Mixtures

-0.50

mix

-0.49

CRR

-0.47

 Confusion

-0.47

onomous

-0.46

Mix

-0.46

POSITIVE LOGITS

shape

0.69

 shape

0.67

 يتيمه

0.61

LookAnd

0.60

extAlignment

0.59

 shapes

0.58

sum

0.57

fortawesome

0.53

QName

0.53

 pprint

0.52

Activations Density 0.156%

syntax and structure specific to programming or data manipulation within Python, particularly related to DataFrames

No Comments

No Known Activations