INDEX

Explanations

discussions related to technology and computer systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 sonst

-0.54

InjectMocks

-0.52

 otherwise

-0.47

 anggaran

-0.47

PADDING

-0.47

-0.46

BagConstraints

-0.46

kwij

-0.45

 ketiga

-0.45

ėk

-0.45

POSITIVE LOGITS

رشف

0.80

parsedMessage

0.78

fromCharCode

0.73

InputTagHelper

0.72

richTextPanel

0.70

 Signalez

0.70

цездатний

0.68

Xna

0.65

himovic

0.64

Personendaten

0.63

Activations Density 6.275%

discussions related to technology and computer systems

No Comments

No Known Activations