INDEX

Explanations

descriptions of conditions or traits

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

ArgsConstructor

-0.56

_));

-0.55

 noastre

-0.50

ьогодні

-0.50

mtliche

-0.50

"]/

-0.49

"]];

-0.49

раздо

-0.49

tacles

-0.48

berapa

-0.48

POSITIVE LOGITS

InjectAttribute

0.79

SharedDtor

0.70

 Afghan

0.66

fight

0.66

 AssemblyCulture

0.64

 Braxton

0.63

StructEnd

0.62

RenderAtEndOf

0.61

Manbalar

0.60

 fight

0.60

Activations Density 0.111%

descriptions of conditions or traits

No Comments

No Known Activations