INDEX

Explanations

references to height or elevation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

لينكات

-0.54

市镇

-0.51

uttgart

-0.48

jsxFileName

-0.47

databinding

-0.46

avista

-0.43

 imprim

-0.43

hosa

-0.43

NegativeButton

-0.43

 minuten

-0.43

POSITIVE LOGITS

 heights

1.34

 height

1.27

 elevation

1.20

 Height

1.15

 Elevation

1.08

 HEIGHT

1.05

 elevations

1.05

 Above

1.04

HEIGHT

1.04

 altitude

1.04

Activations Density 0.443%

references to height or elevation

No Comments

No Known Activations