INDEX

Explanations

the word "ura" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ostavi

-0.93

 تضيفلها

-0.78

 protoimpl

-0.77

ReusableCell

-0.72

 unknownFields

-0.71

 مرئيه

-0.68

 MainAxisSize

-0.64

SourceChecksum

-0.64

///</

-0.63

POSITIVE LOGITS

 mins

0.67

 Mars

0.62

ura

0.59

TODO

0.58

nd

0.56

iries

0.55

nd

0.55

 historique

0.54

Hay

0.51

육

0.50

Activations Density 0.094%

the word "ura" in various contexts

No Comments

No Known Activations