INDEX

Explanations

code snippets involving data handling and plotting in Python

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 صوتيه

-0.74

 Chwiliwch

-0.73

kloped

-0.69

SequentialGroup

-0.67

 saites

-0.66

 Signalez

-0.62

 चीज़ों

-0.61

 كومونز

-0.60

balleur

-0.60

 continuant

-0.60

POSITIVE LOGITS

**

0.69

↵

0.67

**

0.64

dry

0.58

False

0.55

 prome

0.54

True

0.54

ughter

0.52

 sportivo

0.51

iverr

0.51

Activations Density 0.108%

code snippets involving data handling and plotting in Python

No Comments

No Known Activations