INDEX

Explanations

hashtags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 zvuky

-0.74

 onCancelled

-0.71

ViewFeatures

-0.63

 saites

-0.62

eseorang

-0.62

Personensuche

-0.59

)_/¯

-0.56

 AssemblyCulture

-0.56

 مواليد

-0.53

 onCreateView

-0.52

POSITIVE LOGITS

1.01

Portale

0.77

 hashtag

0.75

\#

0.69

.#

0.69

 autorytatywna

0.69

calyp

0.68

TagMode

0.67

!#

0.67

Activations Density 0.122%

hashtags

No Comments

No Known Activations