INDEX

Explanations

references to prior studies and claims of novelty in research

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Lycka

-0.35

 muerta

-0.32

forming

-0.30

Empereur

-0.29

 forming

-0.29

 permitido

-0.28

 stras

-0.27

 trajo

-0.27

 declarado

-0.26

 gestaltet

-0.25

POSITIVE LOGITS

 فريبيس

0.73

twimg

0.67

ValueStyle

0.61

AccessorTable

0.61

SharedCtor

0.59

TargetException

0.58

 NSCoder

0.58

bootstrapcdn

0.58

VIAF

0.57

withIdentifier

0.57

Activations Density 0.662%

references to prior studies and claims of novelty in research

No Comments

No Known Activations