INDEX

Explanations

details related to experimental methods and procedures

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

Following "the," "same," or comparing similar things

np_acts-logits-general · gemini-2.0-flash

same or similar procedures and rules

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

majánló

-0.63

 <>",

-0.62

 disambiguazione

-0.61

genodigd

-0.59

 незавершена

-0.55

__':

-0.54

pecabe

-0.52

ORAGE

-0.51

 automatiques

-0.51

antası

-0.51

POSITIVE LOGITS

 same

1.01

 similar

0.90

same

0.89

Same

0.84

 identical

0.84

 Same

0.81

 Similar

0.71

similar

0.68

Similar

0.68

 dieselben

0.66

Activations Density 0.669%

details related to experimental methods and procedures

Following "the," "same," or comparing similar things

same or similar procedures and rules

No Comments

No Known Activations