INDEX

Explanations

quantitative performance metrics and statistical analyses in research studies

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

Datuak

-0.56

发表于

-0.51

uglify

-0.50

/**

-0.47

Schedulers

-0.45

PIA

-0.45

diger

-0.45

hoof

-0.45

 useAuth

-0.45

Collegamenti

-0.44

POSITIVE LOGITS

 Normdatei

0.76

 jspb

0.59

atiche

0.58

結果は

0.56

DoubleQuotes

0.55

 ecclesias

0.54

 alcanzó

0.54

signol

0.53

 оказалось

0.53

 allemaal

0.53

Activations Density 1.628%

quantitative performance metrics and statistical analyses in research studies

No Comments

No Known Activations