INDEX

Explanations

comments and annotations in programming code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

فایل‌لار

-0.54

<bos>

-0.48

↵↵↵

-0.47

 appunto

-0.47

 muitas

-0.42

webElementXpaths

-0.42

glTexCoord

-0.41

 potest

-0.41

<eos>

-0.41

PostExecute

-0.40

POSITIVE LOGITS

 initComponents

0.72

曖昧さ回避

0.70

orcid

0.63

PRWEB

0.62

utives

0.62

PARATUS

0.61

 تضيفلها

0.60

ländische

0.60

ttino

0.60

fortawesome

0.60

Activations Density 0.178%

comments and annotations in programming code

No Comments

No Known Activations