INDEX

Explanations

expressions of gratitude or appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Mog

-0.81

Rig

-0.68

Mog

-0.68

Rig

-0.66

ext

-0.65

ModelForm

-0.64

ing

-0.63

Hud

-0.62

StringVar

-0.62

Meg

-0.61

POSITIVE LOGITS

 appreciate

1.59

reciate

1.50

 appreci

1.43

 Appreciate

1.43

 appreciates

1.40

 appreciation

1.39

 appreciative

1.37

Appreciate

1.37

 appreciated

1.36

reciation

1.34

Activations Density 0.037%

expressions of gratitude or appreciation

No Comments

No Known Activations