INDEX

Explanations

technical terms related to artificial neural networks and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

OrNil

-0.55

台北

-0.42

jo

-0.41

جغرافيا

-0.41

iske

-0.41

臺北

-0.41

 moral

-0.39

 whether

-0.38

 otherwise

-0.38

bes

-0.38

POSITIVE LOGITS

 ffilmiau

0.69

__(/*!

0.69

ArrowToggle

0.67

naments

0.64

 betweenstory

0.64

تقاوى

0.63

Šaltiniai

0.62

 <>",

0.62

utilisons

0.61

tonode

0.61

Activations Density 0.917%

technical terms related to artificial neural networks and their components

No Comments

No Known Activations