INDEX

Explanations

phrases related to determining conditions and outcomes, particularly in legal and procedural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 Administrativna

-0.85

 otomatig

-0.73

 caufe

-0.69

المناصب

-0.69

titleMargin

-0.67

 الدولى

-0.66

mobileqq

-0.65

 bezeichneter

-0.64

ltk

-0.64

حوالہ

-0.64

POSITIVE LOGITS

 problem

0.52

ex

0.48

事的

0.48

viewBox

0.47

fre

0.47

aturday

0.46

peli

0.46

katalog

0.45

 idée

0.44

APORE

0.44

Activations Density 1.011%

phrases related to determining conditions and outcomes, particularly in legal and procedural contexts

No Comments

No Known Activations