INDEX

Explanations

specific names and titles related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 autorytatywna

-0.75

 مشين

-0.74

 bezeichneter

-0.72

ReusableCell

-0.69

AnchorStyles

-0.66

 Audiodateien

-0.64

 Helico

-0.62

abestanden

-0.62

OwnProperty

-0.61

 Metabol

-0.60

POSITIVE LOGITS

HideFlags

0.64

 ahol

0.57

Pyx

0.56

 akik

0.56

AxisAlignment

0.54

CWE

0.53

ABETH

0.53

thâu

0.51

onedDateTime

0.49

：“……”

0.49

Activations Density 2.590%

specific names and titles related to various topics

No Comments

No Known Activations