INDEX

Explanations

requests for feedback or interaction

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

Informal internet language and emoticons

np_acts-logits-general · gemini-2.0-flash

"I" followed by verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Covid

-1.40

 COVID

-1.39

COVID

-1.31

Covid

-1.28

 covid

-1.28

-1.24

covid

-1.20

https

-1.18

 pandemia

-1.18

 https

-1.13

POSITIVE LOGITS

 idéia

1.16

 definately

1.11

^_^

1.01

myspace

0.89

=)

0.86

 biß

0.85

-_-

0.82

-.-

0.79

 wierd

0.77

 Diarsipkan

0.76

Activations Density 1.035%

requests for feedback or interaction

Informal internet language and emoticons

"I" followed by verbs

No Comments

No Known Activations