INDEX

Explanations

references to null values 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mybatisplus

-0.72

 kasarigan

-0.68

ioutil

-0.59

곱

-0.56

iastes

-0.56

SqlClient

-0.55

 Verbs

-0.53

:][

-0.53

ViewImports

-0.52

 speak

-0.52

POSITIVE LOGITS

 null

0.96

достатки

0.69

</thead>

0.67

utriche

0.62

 econó

0.60

null

0.59

ientôt

0.59

orothy

0.58

󠁢

0.58

 Nana

0.57

Activations Density 0.126%

references to null values in programming contexts

No Comments

No Known Activations