INDEX

Explanations

phrases related to questioning or uncertainty in discussions

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

Follows a question mark

np_acts-logits-general · gemini-2.0-flash

legalistic or technical jargon

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

 diatas

-0.69

 данного

-0.69

 gdyż

-0.68

 didalam

-0.64

の為

-0.63

 Somit

-0.63

 данной

-0.62

"=>

-0.61

 utilizing

-0.61

 již

-0.61

POSITIVE LOGITS

というわけで

0.92

 Presumably

0.82

 disambiguazione

0.75

Dunno

0.74

FWIW

0.74

Heh

0.73

 offenbar

0.71

Tē

0.68

].)

0.67

 cherchés

0.67

Activations Density 0.601%

phrases related to questioning or uncertainty in discussions

Follows a question mark

legalistic or technical jargon

No Comments

No Known Activations