INDEX

Explanations

measurements and units related to size or dimensions

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

BMD

-0.74

 Kości

-0.66

*~*~

-0.64

OCCURRED

-0.61

 treat

-0.61

CAS

-0.60

 bate

-0.60

itaan

-0.59

shadowOpacity

-0.59

 cach

-0.58

POSITIVE LOGITS

cm

2.02

cm

1.88

 centimeter

1.42

 centimeters

1.41

CM

1.35

CM

1.30

Cm

1.27

Cm

1.23

 centimetres

1.20

 centímetros

1.15

Activations Density 0.087%

measurements and units related to size or dimensions

No Comments

No Known Activations