INDEX

Explanations

terms and statistics related to data analysis and presentation of results

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

 يتيمه

-0.66

 مرئيه

-0.59

Réalisation

-0.53

 transfieras

-0.52

FunctionFlags

-0.52

 traditionnels

-0.51

fjspx

-0.50

NameInMap

-0.49

RetentionPolicy

-0.49

POSITIVE LOGITS

 observations

0.84

 categorical

0.81

 observed

0.77

 frequencies

0.76

 Frequencies

0.75

 Observed

0.72

 OBSERV

0.71

 frequency

0.71

 counts

0.70

Observed

0.70

Activations Density 1.722%

terms and statistics related to data analysis and presentation of results

No Comments

No Known Activations