INDEX

Explanations

terms related to biological processes and systems, particularly in the context of energy regulation and metabolic functions

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

Punctuation followed by capitalized words

np_acts-logits-general · gemini-2.0-flash

citations and entities

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

 sanitaires

-0.68

 eletrônico

-0.66

 NDEBUG

-0.63

 domestiques

-0.63

 nôtre

-0.63

 pitié

-0.61

 honte

-0.61

 alimentaires

-0.61

 médicaux

-0.60

 Ahnung

-0.59

POSITIVE LOGITS

 Италијани

1.18

protoimpl

1.09

 autorytatywna

1.04

 ModelExpression

0.95

}));

0.91

 Chwiliwch

0.90

]));

0.89

])):

0.88

OGND

0.87

RegressionTest

0.84

Activations Density 0.645%

terms related to biological processes and systems, particularly in the context of energy regulation and metabolic functions

Punctuation followed by capitalized words

citations and entities

No Comments

No Known Activations