INDEX

Explanations

comments and annotations in the code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ReusableCell

-0.67

 Paglinawan

-0.62

IVEREF

-0.59

bootstrapcdn

-0.58

Parcelize

-0.56

IUrlHelper

-0.56

enumi

-0.55

তথ্যসূত্র

-0.54

 виправивши

-0.54

MethodImpl

-0.53

POSITIVE LOGITS

Pfalz

0.62

脚注の使い方

0.62

#+#

0.61

큼

0.59

 regra

0.59

riages

0.58

'&:

0.57

PCs

0.56

zeh

0.56

Activations Density 0.059%

comments and annotations in the code

No Comments

No Known Activations