INDEX

Explanations

the start of new sections or introduce new topics within a document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

 again

-0.49

-0.45

 just

-0.45

-0.44

den

-0.44

há

-0.43

いただけ

-0.41

ans

-0.41

ben

-0.41

in

-0.40

POSITIVE LOGITS

,:);

0.88

Personendaten

0.85

 Normdatei

0.84

transQ

0.82

webElementXpaths

0.82

 myſelf

0.79

ſelf

0.78

 fubject

0.78

ſelves

0.77

 EconPapers

0.77

Activations Density 0.052%

the start of new sections or introduce new topics within a document

No Comments

No Known Activations