INDEX

Explanations

terms related to randomization 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

الحياه

-0.67

GetAxis

-0.62

 igenom

-0.61

 sepen

-0.57

 صوتيه

-0.57

 onPostExecute

-0.54

 autrefois

-0.53

 proprement

-0.53

olyte

-0.53

esri

-0.53

POSITIVE LOGITS

 random

4.35

Random

4.32

random

4.31

 Random

4.29

 RANDOM

3.86

 randomly

3.46

RANDOM

3.43

随机

3.02

 randomness

2.78

 randomized

2.57

Activations Density 0.105%

terms related to randomization in various contexts

No Comments

No Known Activations