INDEX

Explanations

keywords related to programmatic declarations or constants in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 समीक्षाओं

-0.65

DockStyle

-0.61

 quæ

-0.61

IsContent

-0.59

 surla

-0.59

 sẻ

-0.58

WebVitals

-0.57

 Italij

-0.57

 jsPsych

-0.56

WebServlet

-0.55

POSITIVE LOGITS

 final

0.85

ագրություններ

0.68

readonly

0.66

final

0.64

 fina

0.59

 readonly

0.58

 const

0.57

istoitu

0.55

PhysRev

0.54

 theo

0.50

Activations Density 0.258%

keywords related to programmatic declarations or constants in code

No Comments

No Known Activations