INDEX

Explanations

entities or names of researchers and their affiliations

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

 regular

-0.58

aziland

-0.50

REGULAR

-0.48

별

-0.48

foul

-0.47

ozo

-0.47

 Regular

-0.47

peated

-0.46

 foul

-0.45

Regular

-0.45

POSITIVE LOGITS

帖最后由

0.76

 يتيمه

0.75

 iprot

0.71

 Monfieur

0.69

 defaultstate

0.68

ArrowToggle

0.68

 مرئيه

0.65

 uſed

0.64

 indisponible

0.64

 himſelf

0.63

Activations Density 0.175%

entities or names of researchers and their affiliations

No Comments

No Known Activations