INDEX

Explanations

references to routes and route-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

olsom

-0.83

msford

-0.78

 bezeichneter

-0.77

 Folsom

-0.76

 وتسجيلات

-0.76

eclared

-0.73

хьтан

-0.71

reactstrap

-0.69

TAINMENT

-0.69

IntegerField

-0.69

POSITIVE LOGITS

 routes

1.68

 Routes

1.66

 Route

1.65

 route

1.56

Route

1.49

route

1.43

Routes

1.40

 ROUTE

1.37

routes

1.29

ROUTE

1.25

Activations Density 0.066%

references to routes and route-related terminology

No Comments

No Known Activations