INDEX

Explanations

information related to releases and publications, specifically of books and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

webElementXpaths

-0.64

Ответить

-0.55

InstrumentedTest

-0.54

RenderAtEndOf

-0.54

protoimpl

-0.50

goti

-0.48

setArguments

-0.47

InputTagHelper

-0.47

atuor

-0.46

 erstre

-0.46

POSITIVE LOGITS

 release

2.68

 released

2.63

 releasing

2.34

 releases

2.29

 Released

2.22

 Release

2.20

release

2.19

released

2.16

Released

2.10

 published

2.09

Activations Density 0.403%

information related to releases and publications, specifically of books and media

No Comments

No Known Activations