INDEX

Explanations

programming-related terms and structures, particularly in Java

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

 initComponents

-1.01

Portale

-0.87

WithIOException

-0.86

ViewFeatures

-0.82

parsedMessage

-0.81

abestanden

-0.81

///</

-0.76

RegressionTest

-0.76

 doInBackground

-0.75

oredCriteria

-0.74

POSITIVE LOGITS

 object

0.52

 thing

0.51

ACEAE

0.47

 nature

0.46

ér

0.46

 number

0.41

ol

0.41

0.40

 nhiên

0.40

rep

0.40

Activations Density 0.915%

programming-related terms and structures, particularly in Java

No Comments

No Known Activations