INDEX

Explanations

structured data and relationships within code snippets or programming language syntax

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

AddTagHelper

-0.55

belajaran

-0.47

 محفوظة

-0.47

isman

-0.47

 instanceof

-0.46

 Brain

-0.46

 présidentielle

-0.46

σμο

-0.45

ыгана

-0.45

 Ihnen

-0.45

POSITIVE LOGITS

 themſelves

0.65

 RoutedEventArgs

0.64

ⓧ

0.62

 مشين

0.61

 صوتيه

0.61

RectangleBorder

0.58

Personensuche

0.57

 EventArgs

0.57

 Tapatalk

0.57

StoreMessageInfo

0.56

Activations Density 0.424%

structured data and relationships within code snippets or programming language syntax

No Comments

No Known Activations