INDEX

Explanations

references to specific statistical tests or methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

DOCTYPE

-0.74

 gynhyrchwyd

-0.73

 externi

-0.71

NewUrlParser

-0.68

ollectionView

-0.67

).__

-0.64

yntaxException

-0.62

TestingModule

-0.61

ContentAsync

-0.59

 xenia

-0.59

POSITIVE LOGITS

 оригіналу

0.62

 الرياضيه

0.43

 comigo

0.42

HandlerContext

0.39

Jegyzetek

0.38

િક

0.38

crose

0.38

addContainerGap

0.38

Espèce

0.38

 dernières

0.38

Activations Density 0.296%

references to specific statistical tests or methodologies

No Comments

No Known Activations