INDEX

Explanations

statements and phrases related to dialogue or speech acts

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

Followed by verbs

np_acts-logits-general · gemini-2.0-flash

He said he himself

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Millennium

-0.36

 Paper

-0.34

parseColor

-0.33

Pod

-0.31

 Geothermal

-0.31

 Novo

-0.31

 çalışan

-0.30

 cookie

-0.29

 Innovative

-0.29

 soru

-0.29

POSITIVE LOGITS

himself

0.66

 zijne

0.65

 nahilalakip

0.65

 himſelf

0.62

 Himself

0.61

 himself

0.61

ftagPool

0.61

rungsseite

0.59

iſchen

0.59

+#+#

0.59

Activations Density 0.524%

statements and phrases related to dialogue or speech acts

Followed by verbs

He said he himself

No Comments

No Known Activations