INDEX

Explanations

references to reading and accessing information in the context of digital content or documents

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

 CURIAM

-0.65

 dAtA

-0.65

ilanth

-0.60

cinogenicity

-0.58

hasis

-0.55

 &___

-0.54

țiilor

-0.54

 originaux

-0.54

 MonoBehaviour

-0.54

SerializedSize

-0.54

POSITIVE LOGITS

bootstrapcdn

0.79

 Signalez

0.74

SuspendLayout

0.71

таратура

0.68

!*\

0.63

inflater

0.63

ensement

0.61

WebVitals

0.61

errHandler

0.61

@"/

0.58

Activations Density 0.028%

references to reading and accessing information in the context of digital content or documents

No Comments

No Known Activations