INDEX

Explanations

references to products or terms related to "Bo" or "Botox"

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

"Bo" followed by other characters

np_acts-logits-general · gemini-2.0-flash

Bo- prefixes or starting words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ghalaya

-0.50

isinstance

-0.50

sprogramm

-0.50

Weblinks

-0.47

@[+][

-0.46

})));

-0.45

mehr

-0.44

 himo

-0.43

}:${

-0.43

'',

-0.43

POSITIVE LOGITS

Bo

0.93

Bo

0.90

Hozzáférés

0.82

InputBorder

0.79

 Boch

0.76

 Bost

0.74

Boe

0.73

 Boll

0.72

 defaultstate

0.71

 Bolo

0.70

Activations Density 0.137%

references to products or terms related to "Bo" or "Botox"

"Bo" followed by other characters

Bo- prefixes or starting words

No Comments

No Known Activations