INDEX

Explanations

terms related to professional sectors, scientific initiatives, and community engagement within various contexts

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

 esetén

-1.03



-0.86

 ujednoznacz

-0.83

OOTDTY

-0.78

Portály

-0.73

Hentet

-0.72

 étrangère

-0.69

 Houſe

-0.67

excellents

-0.65

gendes

-0.64

POSITIVE LOGITS

 itself

0.67

iniest

0.59

 της

0.56

ollectionView

0.56

SourceChecksum

0.53

iest

0.52

aarrggbb

0.52

mPaint

0.52

 portion

0.52

readdir

0.51

Activations Density 5.618%

terms related to professional sectors, scientific initiatives, and community engagement within various contexts

No Comments

No Known Activations