INDEX

Explanations

references to collections of written works

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.61

providedIn

-0.56

 дописавши

-0.55

andExpect

-0.52

getMenuInflater

-0.48

 none

-0.48

 kaarangay

-0.45

guenos

-0.45

arget

-0.44

flexDirection

-0.43

POSITIVE LOGITS

 excerpts

0.63

Œuvres

0.62

 facsimile

0.60

ByPrimaryKey

0.59

 verbatim

0.59

 reconstructed

0.59

IVersion

0.58

 integrale

0.58

 mutilated

0.57

 excerpt

0.57

Activations Density 0.452%

references to collections of written works

No Comments

No Known Activations