INDEX

Explanations

references to habits and routines

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)(((

-0.78

SpringRunner

-0.77

imab

-0.64

 реа

-0.62

WriteLiteral

-0.60

Gub

-0.60

 candidatura

-0.60

ildi

-0.60

 لينك

-0.59

 שוליים

-0.59

POSITIVE LOGITS

 habits

1.41

 Habits

1.39

 Habit

1.30

 habit

1.27

Habit

1.23

 habitudes

1.20

 tradition

1.05

 hábito

0.95

habit

0.95

 Tradition

0.95

Activations Density 0.157%

references to habits and routines

No Comments

No Known Activations