INDEX

Explanations

terms related to programming or scripting concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 πως

-0.69

Tikang

-0.69

 autorytatywna

-0.68

Rhestr

-0.67

 disambiguazione

-0.63

 Amongst

-0.62



-0.61

 PeEnEo

-0.60

 otomatig

-0.57

Тарихы

-0.57

POSITIVE LOGITS

 XNUMX

0.61

0.58

0.49

NUMX

0.35

 évé

0.33

 spørsmål

0.33

 advanced

0.32

EnableWeb

0.31

 trusted

0.31

 zufolge

0.30

Activations Density 0.032%

terms related to programming or scripting concepts

No Comments

No Known Activations