INDEX

Explanations

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 المعيارى

-0.83

 typelib

-0.80

 kasarigan

-0.77

WriteTagHelper

-0.74

EndProject

-0.70

tvguidetime

-0.69

 '\\;'

-0.69

RectangleBorder

-0.66

Personensuche

-0.65

]")]

-0.64

POSITIVE LOGITS

ciating

0.46

ppelin

0.44

jsxFileName

0.42

oa̍t

0.40

ordinates

0.39

 lemb

0.39

 concurred

0.38

 compensated

0.37

tæ

0.37

UrlResolution

0.37

Activations Density 0.262%

proper nouns and names

No Comments

No Known Activations