INDEX

Explanations

references to additional items or aspects related to a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

BeginInit

-0.79

 '\\;'

-0.79

脚注の使い方

-0.75

 getItemCount

-0.73

GraphicsUnit

-0.71

owohl

-0.70

("")]

-0.69

("")]

-0.68

 Roskov

-0.67

Pautan

-0.65

POSITIVE LOGITS

 finally

0.50

but

0.49

 essencial

0.44

 HasFactory

0.44

 EXCEPT

0.43

 including

0.43

最後に

0.42

 except

0.41

let

0.41

 infine

0.41

Activations Density 0.376%

references to additional items or aspects related to a topic

No Comments

No Known Activations

references to additional items or aspects related to a topic

No Comments

No Known Activations