INDEX

Explanations

phrases that denote methodological contexts and procedural steps

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

principalColumn

-1.18

principalTable

-1.14

 ivelany

-1.07

XmlAccessType

-1.03

 ddelweddau

-1.02

 <>",

-1.01

Jeografia

-1.00

rrggbb

-0.97

 فريبيس

-0.97

 otomatig

-0.96

POSITIVE LOGITS

In

0.71

hogy

0.70

In

0.63

しかし

0.62

 addition

0.60

 this

0.59

xious

0.58

 importantly

0.58

noy

0.57

As

0.57

Activations Density 0.504%

phrases that denote methodological contexts and procedural steps

No Comments

No Known Activations