INDEX

Explanations

emotional responses, particularly related to anger and frustration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

modelBuilder

-0.74

 autorytatywna

-0.70

 BrowserModule

-0.65

Seeder

-0.65

telser

-0.63

ondis

-0.62

dora

-0.59

eken

-0.58

 merveille

-0.57

isNullOrEmpty

-0.56

POSITIVE LOGITS

 anger

1.41

 angry

1.40

 Anger

1.32

angry

1.28

 Angry

1.26

Angry

1.26

Anger

1.21

 enoj

1.17

 colère

1.17

 rage

1.16

Activations Density 0.144%

emotional responses, particularly related to anger and frustration

No Comments

No Known Activations