INDEX

Explanations

the beginning of sequences or phrases, indicating transitions or new topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 autorytatywna

-0.85

stateMutability

-0.76

awtextra

-0.75

ⓧ

-0.72

 continúas

-0.72

 disambiguazione

-0.71

@[+][

-0.71

 Chwiliwch

-0.70

ArgsConstructor

-0.67

Cyfeiriadau

-0.66

POSITIVE LOGITS

 kautta

0.48

 souri

0.42

émica

0.42

TagMode

0.41

 propres

0.41

ialak

0.40

 kjem

0.40

 écl

0.40

 történ

0.40

 kræ

0.39

Activations Density 0.018%

the beginning of sequences or phrases, indicating transitions or new topics

No Comments

No Known Activations