INDEX

Explanations

references to statistical or mathematical concepts related to data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

पया

-0.71

 Referential

-0.68

Rüyada

-0.63

Autoritní

-0.57

 soprav

-0.56

 копия

-0.56

 Refugees

-0.55

MessageOf

-0.53

Hauptartikel

-0.51

principalColumn

-0.51

POSITIVE LOGITS

InteropServices

0.71

 الحره

0.69

 springfox

0.59

enames

0.57

AutoModerator

0.56

antiate

0.54

ifferentiated

0.54

zędu

0.54

wixt

0.52

MetaObject

0.52

Activations Density 1.157%

references to statistical or mathematical concepts related to data analysis

No Comments

No Known Activations