INDEX

Explanations

references to administrative interfaces and management tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

msgTypes

-0.70

__(/*!

-0.68

patent

-0.65

GenerationType

-0.62

exitRule

-0.60

BindingResult

-0.60

følgelig

-0.60

 rhestr

-0.59

GEBURTSDATUM

-0.58

(!__

-0.58

POSITIVE LOGITS

 dashboard

0.70

 Dashboard

0.69

dashboard

0.61

Personendaten

0.60

Dashboard

0.58

 dashboards

0.57

painel

0.57

ashboard

0.56

repr

0.55

 painel

0.55

Activations Density 0.179%

references to administrative interfaces and management tools

No Comments

No Known Activations