INDEX

Explanations

terms related to programming functions and options in code documentation

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

SafeMath

-0.52

onAttach

-0.48

NSError

-0.45

SupportActionBar

-0.45

glPushMatrix

-0.45

 επί

-0.45

 Hände

-0.43

openhague

-0.43

windowFixed

-0.43

 handwriting

-0.43

POSITIVE LOGITS

 propOrder

0.69

OGND

0.67

Tunes

0.60

 Chwiliwch

0.59

таратура

0.59

ConstraintMaker

0.58

 تضيفلها

0.58

DoubleQuotes

0.55

 customize

0.55

ourites

0.54

Activations Density 1.162%

terms related to programming functions and options in code documentation

No Comments

No Known Activations