INDEX

Explanations

terms related to treaties and agreements

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

"a [positive or neutral word]"

np_acts-logits-general · gemini-2.0-flash

a result/wealth/good/compromise/refusal/money/conversation/bitter/part/step

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

Przypisy

-0.68

tanleria

-0.59

 noqa

-0.58

তথ্যসূত্র

-0.52

%)$

-0.51

 collectif

-0.49

сшта

-0.49

 Lordships

-0.48

ukone

-0.48

POSITIVE LOGITS

 most

0.80

most

0.67

 groote

0.60

Most

0.60

 استنادى

0.56

 goodly

0.54

 Spisak

0.54

<?

0.53

föra

0.50

 moft

0.50

Activations Density 0.359%

terms related to treaties and agreements

"a [positive or neutral word]"

a result/wealth/good/compromise/refusal/money/conversation/bitter/part/step

No Comments

No Known Activations