INDEX

Explanations

terms related to size and compactness

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

 ویکی‌پدیا

-0.59

 يتيمه

-0.50

findpost

-0.49

LoadMore

-0.49

Regi

-0.48

glEnable

-0.48

iprot

-0.47

mybatisplus

-0.47

 élevés

-0.46

 ModelExpression

-0.45

POSITIVE LOGITS

 small

2.34

 tiny

2.22

 smaller

2.20

small

2.08

Small

2.04

 SMALL

2.00

Smaller

1.99

 Small

1.96

 Smaller

1.96

smaller

1.92

Activations Density 0.530%

terms related to size and compactness

No Comments

No Known Activations

terms related to size and compactness

No Comments

No Known Activations