INDEX

Explanations

references to selectors and categories related to user interface elements in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

LookAnd

-0.66

 صوتيه

-0.59

MigrationBuilder

-0.59

haviour

-0.58

 defStyleAttr

-0.57

 Tiefe

-0.52

Especies

-0.51

 cárcel

-0.51

 zákaz

-0.51

 estekak

-0.50

POSITIVE LOGITS

Kab

0.73

kab

0.69

 urban

0.68

Kab

0.66

 Hudson

0.63

cab

0.61

Cab

0.60

hood

0.60

CAB

0.58

 Urban

0.56

Activations Density 0.502%

references to selectors and categories related to user interface elements in programming contexts

No Comments

No Known Activations