INDEX

Explanations

terms related to long data types and their variations 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

ArgsConstructor

-0.79

 nargin

-0.68

GHIJKLM

-0.64

 rowspan

-0.64

usepackage

-0.63

ferien

-0.56

[++

-0.55

multirow

-0.55

oredCriteria

-0.52

acana

-0.52

POSITIVE LOGITS

getLong

1.07

long

0.98

setLong

0.90

Long

0.87

 Long

0.86

Hentet

0.85

 LONG

0.82

 long

0.81

LONG

0.80

longValue

0.76

Activations Density 0.123%

terms related to long data types and their variations in programming contexts

No Comments

No Known Activations