INDEX

Explanations

various punctuation and formatting elements, likely focusing on non-alphanumeric characters in a diverse linguistic context

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

Mathematical or statistical notation

np_acts-logits-general · gemini-2.0-flash

greek language and symbols

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.93

-0.92

-0.90

sam

-0.89

del

-0.89

in

-0.89

di

-0.88

to

-0.87

POSITIVE LOGITS

 myſelf

2.25

 itſelf

2.23

 ―――――

2.06

 photolibrary

2.01

 ſind

2.01

 Theſe

1.96

 ་་

1.93

^(@)

1.93

 يتيمه

1.88

 Monfieur

1.86

Activations Density 0.020%

various punctuation and formatting elements, likely focusing on non-alphanumeric characters in a diverse linguistic context

Mathematical or statistical notation

greek language and symbols

No Comments

No Known Activations