INDEX

Explanations

numerical data and values

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

 '\\;'

-1.00

webElementXpaths

-0.96

цездатний

-0.92

oredCriteria

-0.92

 autorytatywna

-0.90

InjectAttribute

-0.89

رشف

-0.86

featureID

-0.85

MessageOf

-0.84

 utafitiHapana

-0.81

POSITIVE LOGITS

Lö

0.50

Dro

0.47

Wys

0.47

GQ

0.46

uva

0.46

 indiv

0.46

APT

0.45

uga

0.45

 Scro

0.44

жли

0.43

Activations Density 0.106%

numerical data and values

No Comments

No Known Activations