INDEX

Explanations

data related to physical attributes and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ujednoznacz

-0.56

 EClass

-0.46

ソッド

-0.45

ReusableCell

-0.45

 quantity

-0.43

mappedBy

-0.43

addHandler

-0.43

leigh

-0.43

 innovate

-0.42

numerusform

-0.42

POSITIVE LOGITS

 tall

1.43

 taller

1.23

 Tall

1.15

tall

1.14

Tall

1.12

 TALL

1.08

 tallest

1.08

 height

0.97

 stature

0.91

taller

0.90

Activations Density 0.202%

data related to physical attributes and measurements

No Comments

No Known Activations