INDEX

Explanations

references related to decision-making and weighing consequences, particularly in moral and financial contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 protoimpl

-0.60

assertNotNull

-0.53

ophora

-0.52

 esfera

-0.51

 Zenith

-0.51

Gay

-0.50

veston

-0.48

ondissement

-0.48

 Öster

-0.47

Източници

-0.46

POSITIVE LOGITS

StoryboardSegue

0.79

 initComponents

0.66

 sacrificing

0.62

IntoConstraints

0.61

 sacrificed

0.60

 متعلقه

0.59

tvguidetime

0.59

 sacrifice

0.56

脚注の使い方

0.56

ⓧ

0.54

Activations Density 0.363%

references related to decision-making and weighing consequences, particularly in moral and financial contexts

No Comments

No Known Activations