INDEX

Explanations

numerical values and associated scientific terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

aarrggbb

-0.52

hyrchwyd

-0.45

省市镇

-0.43

 Kond

-0.43

 Dore

-0.40

 expla

-0.40

tieron

-0.40

swiper

-0.40

 query

-0.38

हाय

-0.38

POSITIVE LOGITS

 NSCoder

0.76

enumi

0.70



0.70

WriteTagHelper

0.68

Datuak

0.68

CrossRef

0.65

AnimationsModule

0.63

Попис

0.62

@"/

0.62

Activations Density 0.552%

numerical values and associated scientific terminology

No Comments

No Known Activations