INDEX

Explanations

occurrences of initialization and line reference patterns in Python code

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

Portale

-0.67

 الحره

-0.59

 naman

-0.58

 năng

-0.53

 Jens

-0.52

itano

-0.52

Lugares

-0.52

setOptions

-0.51

penta

-0.50

뀜

-0.49

POSITIVE LOGITS

ViewFeatures

0.86

 مشين

0.68

 виправивши

0.68

SizeF

0.64

GOTREF

0.61

PasswordEncoder

0.57

 propOrder

0.57

তথ্যসূত্র

0.56

providedIn

0.55

TabStop

0.55

Activations Density 0.037%

occurrences of initialization and line reference patterns in Python code

No Comments

No Known Activations