INDEX

Explanations

the usage of the word "proper."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Šaltiniai

-0.60

 الاطلاع

-0.57

 examinations

-0.51

onAttach

-0.50

তা

-0.50

Hauptartikel

-0.49

 consultato

-0.49

_()

-0.48

audiovisuel

-0.47

ņa

-0.47

POSITIVE LOGITS

 AssemblyCulture

1.05

 שוליים

0.76

proper

0.75

ագրություններ

0.73

 proper

0.67

Software

0.66

 فريبيس

0.63

 Proper

0.63

SOFTWARE

0.62

 CreateTagHelper

0.62

Activations Density 0.149%

the usage of the word "proper."

No Comments

No Known Activations