INDEX

Explanations

mathematical expressions and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 defStyleAttr

-0.79

 snippetHide

-0.71

UnsafeEnabled

-0.70

MLLoader

-0.69

Jereo

-0.67

findpost

-0.67

Espèce

-0.67

 CommonModule

-0.67

})`

-0.67

Personendaten

-0.67

POSITIVE LOGITS

dfrac

0.55

ยว

0.53

enumi

0.49

ggior

0.48

frac

0.47

 ensino

0.47

tfrac

0.46

közi

0.46

ároz

0.44

 ngân

0.44

Activations Density 1.061%

mathematical expressions and notations

No Comments

No Known Activations