INDEX

Explanations

tables or structured data formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surla

-0.69

MLLoader

-0.66

AddHtmlAttribute

-0.63

<?

-0.60



-0.58

MessageTagHelper

-0.56

amodel

-0.56

webElementXpaths

-0.55

UserScript

-0.54

orghini

-0.54

POSITIVE LOGITS

#+#

0.70

 Numerade

0.38

 mesmos

0.31

เดิม

0.30

 méri

0.30

 ordinaires

0.29

rät

0.29

że

0.29

 comigo

0.29

 CGRect

0.28

Activations Density 0.000%

tables or structured data formats

No Comments

No Known Activations