INDEX

Explanations

elements related to requests or inquiries for information and assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

StringCopy

-0.62

Népesség

-0.59

 Autorisations

-0.59

 assoluto

-0.56

日閲覧

-0.56

RUnlock

-0.56

 ErrInvalid

-0.54

 BoxFit

-0.54

 alimentaires

-0.54

vaders

-0.54

POSITIVE LOGITS

الإنجليزية

0.66

 autorytatywna

0.55

bootstrapcdn

0.55

舺

0.55

bkz

0.53

randomUUID

0.53

pires

0.52

ContentLoaded

0.52

adpleegd

0.52

 GIPHY

0.52

Activations Density 1.414%

elements related to requests or inquiries for information and assistance

No Comments

No Known Activations