INDEX

Explanations

references to modules or modular structures in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Braw

-0.83

 Bellow

-0.74

 Justine

-0.71

 GLFW

-0.71

 Daria

-0.70

 diffe

-0.69

 Krus

-0.69

consulté

-0.68

 Belo

-0.68

 belie

-0.67

POSITIVE LOGITS

 modules

1.87

 Modules

1.72

 module

1.69

 Module

1.62

Modules

1.61

modules

1.56

 MODULE

1.53

MODULE

1.52

Module

1.51

module

1.49

Activations Density 0.080%

references to modules or modular structures in a coding context

No Comments

No Known Activations