INDEX

Explanations

references to balance or equilibrium in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ʊ

-0.64

nezeu

-0.62

Aww

-0.60

PROCEDURE

-0.60

 Biggs

-0.59

ADVERTISEMENT

-0.58

-0.56

 McDaniel

-0.55

 chirurgie

-0.55

 Hooper

-0.55

POSITIVE LOGITS

 balance

3.44

 Balance

3.29

balance

3.27

Balance

3.09

 balances

3.02

 BALANCE

2.96

BALANCE

2.79

balances

2.65

 balanced

2.60

 balancing

2.49

Activations Density 0.041%

references to balance or equilibrium in various contexts

No Comments

No Known Activations