INDEX

Explanations

technical terms related to model execution in programming contexts

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

modelmodel training and architecture

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 editados

-0.24

cue

-0.22

avimas

-0.21

 inconn

-0.20

 murió

-0.19

 importación

-0.19

 convirtió

-0.18

 hyö

-0.18

 privados

-0.18

 naturligt

-0.18

POSITIVE LOGITS

RegressionTest

0.74

SequentialGroup

0.74

WebServlet

0.72

transQ

0.71

WithIOException

0.71

 nahilalakip

0.71

 surla

0.69

FormTagHelper

0.66

stateProvider

0.65

 TestBed

0.63

Activations Density 0.032%

technical terms related to model execution in programming contexts

modelmodel training and architecture

No Comments

No Known Activations