INDEX

Explanations

phrases indicating logical reasoning or conclusions drawn from evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 صوتيه

-1.07

 ویکی‌پدیای

-0.99

oredCriteria

-0.90

yntaxException

-0.85

 beginnetje

-0.83

mybatisplus

-0.82

 otomatig

-0.80

>");

-0.79

MultipartFile

-0.76

AccessFile

-0.76

POSITIVE LOGITS

 that

1.30

 bahwa

0.86

 rằng

0.70

 bahawa

0.63

ว่า

0.60

0.58

KommentareTeilen

0.57

że

0.57

that

0.54

 fact

0.54

Activations Density 1.001%

phrases indicating logical reasoning or conclusions drawn from evidence

No Comments

No Known Activations