INDEX

Explanations

numerical values and their representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

tvguidetime

-0.84

IntoConstraints

-0.83

 BorderRadius

-0.75

 InputDecoration

-0.72

DockStyle

-0.69

 MenuView

-0.68

MessageTagHelper

-0.66

getDoctrine

-0.62

MigrationBuilder

-0.62

+#+#

-0.59

POSITIVE LOGITS

évaluateur

0.53

 aventure

0.48

фом

0.45

AppMethodBeat

0.45

Can

0.45

 مشين

0.44

 initComponents

0.44

addContainerGap

0.43

Can

0.41

Véxase

0.41

Activations Density 0.467%

numerical values and their representations

No Comments

No Known Activations