INDEX

Explanations

terms related to randomness and random selection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

disposing

-0.66

Награды

-0.66

 modelleri

-0.66

Abp

-0.66

 essentiellement

-0.65

 berço

-0.64

 comprometido

-0.60

 estates

-0.60

 lèvres

-0.59

 cricketer

-0.58

POSITIVE LOGITS

 azar

1.11

 RANDOM

1.10

RANDOM

1.08

 Random

1.03

 randomly

1.02

getRandom

1.01

 hasard

0.97

 random

0.95

Random

0.94

random

0.93

Activations Density 0.110%

terms related to randomness and random selection

No Comments

No Known Activations