INDEX

Explanations

locations and their corresponding details or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

featureID

-0.89

WebVitals

-0.83

formik

-0.60

 المعيارى

-0.60

存于互联网档案馆

-0.60

lodash

-0.59

rrggbb

-0.59

 utafitiHapana

-0.59

 оригіналу

-0.58

Parcelize

-0.57

POSITIVE LOGITS

#+#

0.55

 surla

0.51

æn

0.49

 Geiger

0.48

eleri

0.48

ніципа

0.47

umat

0.46

ecta

0.45

OutputStream

0.44

Tanya

0.44

Activations Density 0.080%

locations and their corresponding details or identifiers

No Comments

No Known Activations