INDEX

Explanations

data types and their attributes in programming contexts

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

Diwedd

-0.60

de

-0.55

ân

-0.49

du

-0.49

te

-0.48

lo

-0.46

czaj

-0.45

ve

-0.44

 qualunque

-0.42

LO

-0.42

POSITIVE LOGITS

GenerationType

0.96

sizeCache

0.91

initComponents

0.90

InjectAttribute

0.89

DeleteBehavior

0.88

EDEFAULT

0.87

Brainz

0.87

 propOrder

0.87

 IndexPath

0.86

InSection

0.85

Activations Density 0.093%

data types and their attributes in programming contexts

No Comments

No Known Activations