INDEX

Explanations

references to specific scientific variables, functions, or experimental conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

KURZBESCHREIBUNG

-0.79

 estimés

-0.70

IUrlHelper

-0.63

 DbContext

-0.60

IVEREF

-0.59

הערות

-0.55

Geplaatst

-0.54

üttel

-0.53

tinya

-0.51

CodeAttribute

-0.50

POSITIVE LOGITS

AndEndTag

0.70

Obrázky

0.58

ⓧ

0.58

">—

0.55

wieś

0.50

 Kommission

0.50

kháu

0.47

SequentialGroup

0.44

openzeppelin

0.43

+#+#

0.42

Activations Density 0.352%

references to specific scientific variables, functions, or experimental conditions

No Comments

No Known Activations