INDEX

Explanations

concepts related to emptiness or lack of content, particularly in programming or data contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lenker

-0.61

 kuin

-0.51

dyž

-0.49

 acceptez

-0.48

 Favourite

-0.47

Favourite

-0.46

nanoTime

-0.46

YOU

-0.46

見ると

-0.45

 favoured

-0.45

POSITIVE LOGITS

 empty

1.44

 Empty

1.37

Empty

1.24

 emptiness

1.21

empty

1.20

 EMPTY

1.19

EMPTY

1.05

 kosong

1.03

 vacía

0.99

OrWhiteSpace

0.98

Activations Density 0.565%

concepts related to emptiness or lack of content, particularly in programming or data contexts

No Comments

No Known Activations