INDEX

Explanations

terms and phrases indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

coc

-0.48

Sem

-0.47

mor

-0.46

程式

-0.46

AppMethodBeat

-0.45

longValue

-0.44

udra

-0.44

Gra

-0.44

arai

-0.43

WebControls

-0.42

POSITIVE LOGITS

 CreateTagHelper

0.89

 around

0.84

 alrededor

0.81

 giù

0.79

ByVersion

0.78

 AROUND

0.77

 autour

0.77

 intorno

0.76

 ComVisible

0.75

otriva

0.74

Activations Density 0.113%

terms and phrases indicating relationships or connections

No Comments

No Known Activations