INDEX

Explanations

programming constructs related to class and method definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 snippetHide

-0.99

 AssemblyCompany

-0.82

 surla

-0.82

帖最后由

-0.71

 BoxFit

-0.69

 للمعارف

-0.67

脚注の使い方

-0.65

rungsseite

-0.65

URLException

-0.64

 CreateTagHelper

-0.64

POSITIVE LOGITS

<eos>

0.35

ang

0.29

su

0.29

 lost

0.29

velocityY

0.27

ord

0.27

wi

0.26

vet

0.26

bel

0.26

tor

0.26

Activations Density 0.235%

programming constructs related to class and method definitions

No Comments

No Known Activations