INDEX

Explanations

references to the term "Tre."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

MethodManager

-0.55

ngdoc

-0.55

(!__

-0.54

MethodImpl

-0.53

bootstrapcdn

-0.52

inheritDoc

-0.51

 kasarigan

-0.51

 noqa

-0.49

anywhere

-0.48

 column

-0.48

POSITIVE LOGITS

ագրություններ

0.57

 חיצוניים

0.55

SharedCtor

0.54

 विश्वसनीयता

0.54

aarrggbb

0.53

acherous

0.52

enumerable

0.49

CDATA

0.49

 <>",

0.49

 ContentValues

0.46

Activations Density 0.264%

references to the term "Tre."

No Comments

No Known Activations