INDEX

Explanations

structured data or formatting indicators within technical or programming content

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

IContainer

-0.81

.*")]

-0.71

 nawr

-0.69

 للمعارف

-0.68

 Spisak

-0.68

findpost

-0.67

 photolibrary

-0.66

 بيها

-0.65

RegressionTest

-0.63

ſhip

-0.62

POSITIVE LOGITS

limit

0.53

″

0.52

 which

0.49

Hochspringen

0.49

which

0.49

“

0.49

moveToFirst

0.49

свя

0.47

 đựng

0.46

netbeans

0.46

Activations Density 0.923%

structured data or formatting indicators within technical or programming content

No Comments

No Known Activations