INDEX

Explanations

elements related to technical and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Deploy

-0.70

 iconLine

-0.61

 Deployment

-0.61

 Digit

-0.60

 Troops

-0.59

 begitu

-0.59

mbic

-0.59

 Autó

-0.59

deployed

-0.59

 saites

-0.58

POSITIVE LOGITS

NameInMap

0.72

findpost

0.67

PyExc

0.65

jspx

0.62

msgSender

0.59

 referenties

0.59

queryInterface

0.58

rhosis

0.58

экономи

0.56

 besti

0.55

Activations Density 0.070%

elements related to technical and programming constructs

No Comments

No Known Activations