INDEX

Explanations

references to LED components and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-1.00

 GenerationType

-0.97

 ་་

-0.94

θρώ

-0.93

 MediatR

-0.88

 nakalista

-0.86

 Majefty

-0.86

 houſe

-0.85

Efq

-0.83

 estekak

-0.83

POSITIVE LOGITS

led

0.63

0.58

0.56

 connus

0.56

 Boys

0.54

 connues

0.53

 dunque

0.52

 Presumably

0.51

<eos>

0.51

Activations Density 0.578%

references to LED components and their characteristics

No Comments

No Known Activations